Search

Motion-controlled robotic arms allow a user to interact with a remote real world without physically reaching it. By connecting cyberspace to the physical world, such interactive teleoperations are promising to improve remote education, virtual social interactions and online participatory activities. In this work, we build up a motion-controlled robotic arm framework comprising a robotic arm end and a user end, which are connected via a network and responsible for manipulator control and motion capture respectively. To protect the system access, we propose to verify who is controlling the robotic arm by examining the robotic arm’s behavior, which adds a second security layer in addition to the system login credentials. We show that a robotic arm’s motion inherits its human controller’s behavioral biometric in interactive control scenarios. By extracting the angle readings of the robotic arm’s all joints, the proposed user authentication approach reconstructs the robotic arm’s end-effector movement trajectory that follows the user’s hand. Furthermore, we derive the unique robotic motion features to capture the user’s behavioral biometric embedded in the robot motions and develop learning-based algorithms to verify the robotic arm user to be one of the enrolled users or a nonuser. Extensive experiments show that our system achieves 94% accuracy to distinguish users while preventing user identity spoofing attacks with 95% accuracy.

An estimated 11% of adults report experiencing some form of cognitive decline, which may be associated with conditions such as stroke or dementia and can impact their memory, cognition, behavior, and physical abilities. While there are no known pharmacological treatments for many of these conditions, behavioral treatments such as cognitive training can prolong the independence of people with cognitive impairments. These treatments teach metacognitive strategies to compensate for memory difficulties in their everyday lives. Personalizing these treatments to suit the preferences and goals of an individual is critical to improving their engagement and sustainment, as well as maximizing the treatment's effectiveness. Robots have great potential to facilitate these training regimens and support people with cognitive impairments, their caregivers, and clinicians. This article examines how robots can adapt their behavior to be personalized to an individual in the context of cognitive neurorehabilitation. We provide an overview of existing robots being used to support neurorehabilitation and identify key principles for working in this space. We then examine state-of-the-art technical approaches for enabling longitudinal behavioral adaptation. To conclude, we discuss our recent work on enabling social robots to automatically adapt their behavior and explore open challenges for longitudinal behavior adaptation. This work will help guide the robotics community as it continues to provide more engaging, effective, and personalized interactions between people and robots.

We describe a learning-from-demonstration technique that enables a general-purpose humanoid robot to lead a user through object-mediated upper-limb exercises. It needs only tens of seconds of training data from a therapist teleoperating the robot to do the task with the user. We model the robot behavior as a regression problem, inferring the desired robot effort using the end-effector's state (position and velocity). Compared to the conventional approach of learning time-based trajectories, our strategy produces customized robot behavior and eliminates the need to tune gains to adapt to the user's motor ability. In our study, one occupational therapist and six people with stroke trained a Willow Garage PR2 on three example tasks (periodic 1D and 2D motions plus episodic pick-and-place). They then repeatedly did the tasks with the robot and blindly compared the state- and time-based controllers learned from the training data. Our results show that working models were reliably obtained to allow the robot to do the exercise with the user; that our state-based approach enabled users to be more actively involved, allowed larger excursion, and generated power outputs more similar to the therapist demonstrations; and that the therapist found our strategy more agreeable than the traditional time-based approach.

Although non-verbal cues such as arm movement and eye gaze can convey robot intention, they alone may not provide enough information for a human to fully understand a robot’s behavior. To better understand how to convey robot intention, we conducted an experiment ( N = 366 ) investigating the need for robots to explain , and the content and properties of a desired explanation such as timing , engagement importance , similarity to human explanations, and summarization . Participants watched a video where the robot was commanded to hand an almost-reachable cup and one of six reactions intended to show the unreachability : doing nothing (No Cue), turning its head to the cup (Look), or turning its head to the cup with the addition of repeated arm movement pointed towards the cup (Look & Point), and each of these with or without a Headshake. The results indicated that participants agreed robot behavior should be explained across all conditions, in situ , in a similar manner as what human explain, and provide concise summaries and respond to only a few follow-up questions by participants. Additionally, we replicated the study again with N = 366 participants after a 15-month span and all major conclusions still held.

As autonomous robots continue to be deployed near people, robots need to be able to explain their actions. In this article, we focus on organizing and representing complex tasks in a way that makes them readily explainable. Many actions consist of sub-actions, each of which may have several sub-actions of their own, and the robot must be able to represent these complex actions before it can explain them. To generate explanations for robot behavior, we propose using Behavior Trees (BTs), which are a powerful and rich tool for robot task specification and execution. However, for BTs to be used for robot explanations, their free-form, static structure must be adapted. In this work, we add structure to previously free-form BTs by framing them as a set of semantic sets {goal, subgoals, steps, actions} and subsequently build explanation generation algorithms that answer questions seeking causal information about robot behavior. We make BTs less static with an algorithm that inserts a subgoal that satisfies all dependencies. We evaluate our BTs for robot explanation generation in two domains: a kitting task to assemble a gearbox, and a taxi simulation. Code for the behavior trees (in XML) and all the algorithms is available at github.com/uml-robotics/robot-explanation-BTs.

To integrate social robots in real-life contexts, it is crucial that they are accepted by the users. Acceptance is not only related to the functionality of the robot but also strongly depends on how the user experiences the interaction. Established design principles from usability and user experience research can be applied to the realm of human–robot interaction, to design robot behavior for the comfort and well-being of the user. Focusing the design on these aspects alone, however, comes with certain ethical challenges, especially regarding the user’s privacy and autonomy. Based on an example scenario of human–robot interaction in elder care, this paper discusses how established design principles can be used in social robotic design. It then juxtaposes these with ethical considerations such as privacy and user autonomy. Combining user experience and ethical perspectives, we propose adjustments to the original design principles and canvass our own design recommendations for a positive and ethically acceptable social human–robot interaction design. In doing so, we show that positive user experience and ethical design may be sometimes at odds, but can be reconciled in many cases, if designers are willing to adjust and amend time-tested design principles.

This paper aims in developing an intelligent interactive robot with multi-functions which provides entertainment and companion. To obtain the information accurately, we have used speech recognition to perform the operations. For the Robot behavior, planning, interactions with the voice assistant and interactions with the user the various speech recognition results are applied. The robot has a simple design. In this study, we have used the microphone for speech recognition. In addition, we have used room automation, notice display using voice message of the intelligent interaction between human and robots.

In socially assistive robotics, human activity recognition plays a central role when the adaptation of the robot behavior to the human one is required. In this paper, we present an activity recognition approach for activities of daily living based on deep learning and skeleton data. In the literature, ad hoc features extraction/selection algorithms with supervised classification methods have been deployed, reaching an excellent classification performance. Here, we propose a deep learning approach, combining CNN and LSTM, that exploits both the learning of spatial dependencies correlating the limbs in a skeleton 3D grid representation and the learning of temporal dependencies from instances with a periodic pattern that works on raw data and so without requiring an explicit feature extraction process. These models are proposed for real-time activity recognition, and they are tested on the CAD-60 dataset. Results show that the proposed model behaves better than an LSTM model thanks to the automatic features extraction of the limbs’ correlation. “New Person” results show that the CNN-LSTM model achieves$$95.4\%$$95.4%of precision and$$94.4\%$$94.4%of recall, while the “Have Seen” results are$$96.1\%$$96.1%of precision and$$94.7\%$$94.7%of recall.

To encourage visitors to use guiding agents in public spaces, this study adopted a design approach and focused on identifying behavioral factors that would encourage interaction. Six factors of agent behavior were hypothesized, and an experiment was performed in a public space with real people. One or two communication robots were installed near the entrance of a university library. The reactions of library users passing by the robot were observed and recorded under different robot behavior conditions. The results showed that the robots were able to attract attention by uttering guidance information and looking in various directions while waiting for people. When the robots spoke directly to nearby people, the people tended to interact with them. The results of a questionnaire survey suggested that the voice, speech content, and appearance of the robots are also important factors.

We synthesize shared control protocols subject to probabilistic temporal logic specifications. More specifically, we develop a framework in which a human and an autonomy protocol can issue commands to carry out a certain task. We blend these commands into a joint input to a robot. We model the interaction between the human and the robot as a Markov decision process (MDP) that represents the shared control scenario. Using inverse reinforcement learning, we obtain an abstraction of the human's behavior and decisions. We use randomized strategies to account for randomness in human's decisions, caused by factors such as complexity of the task specifications or imperfect interfaces. We design the autonomy protocol to ensure that the resulting robot behavior satisfies given safety and performance specifications in probabilistic temporal logic. Additionally, the resulting strategies generate behavior as similar to the behavior induced by the human's commands as possible. We solve the underlying problem efficiently using quasiconvex programming. Case studies involving autonomous wheelchair navigation and unmanned aerial vehicle mission planning showcase the applicability of our approach., Comment: Submitted to IEEE Transactions of Automatic Control

Multirobot systems must be able to maintain performance when robots get delayed during execution. For mobile robots, one source of delays is congestion . Congestion occurs when robots deployed in shared physical spaces interact, as robots present in the same area simultaneously must maneuver to avoid each other. Congestion can adversely affect navigation performance and increase the duration of navigation actions. In this article, we present a multirobot planning framework that utilizes learnt probabilistic models of how congestion affects navigation duration. Central to our framework is a probabilistic reservation table , which summarizes robot plans, capturing the effects of congestion. To plan, we solve a sequence of single-robot time-varying Markov automata , where transition probabilities and rates are obtained from the probabilistic reservation table. We also present an iterative model refinement procedure for accurately predicting execution-time robot performance. We evaluate our framework with extensive experiments on synthetic data and simulated robot behavior.

Advancements within human–robot interaction generate increasing opportunities for proximate, goal-directed joint action (GDJA). However, robot errors are common and researchers must determine how to mitigate them. In this article, we examine how expectations for robot functionality affect people’s perceptions of robot reliability and trust for a robot that makes errors. Here 35 participants ( n = 35) performed a collaborative banner-hanging task with an autonomous mobile manipulator (Toyota HSR). Each participant received either a low- or high-functionality framing for the robot. We then measured how participants perceived the robot’s reliability and trust prior to, during, and after interaction. Functionality framing changed how robot errors affected participant experiences of robot behavior. People with low expectations experienced positive changes in reliability and trust after interacting with the robot, while those with high expectations experienced a negative change in reliability and no change in trust. The low-expectation group also showed greater trust recovery following the robot’s first error compared to the high group. Our findings inform human–robot teaming through: (1) identifying robot presentation factors that can be employed to facilitate trust calibration and (2) establishing the effects of framing, functionality, and the interactions between them to improve dynamic models of human–robot teaming.

In this work, we present a new planning formalism called Expectation-Aware planning for decision making with humans in the loop where the human's expectations about an agent may differ from the agent's own model. We show how this formulation allows agents to not only leverage existing strategies for handling model differences but can also exhibit novel behaviors that are generated through the combination of these different strategies. Our formulation also reveals a deep connection to existing approaches in epistemic planning. Specifically, we show how we can leverage classical planning compilations for epistemic planning to solve Expectation-Aware planning problems. To the best of our knowledge, the proposed formulation is the first complete solution to decision-making in the presence of diverging user expectations that is amenable to a classical planning compilation while successfully combining previous works on explanation and explicability. We empirically show how our approach provides a computational advantage over existing approximate approaches that unnecessarily try to search in the space of models while also failing to facilitate the full gamut of behaviors enabled by our framework.

Mobile robots in crowds often have limited navigation capability due to insufficient evaluation of pedestrian behavior. We strengthen this capability by predicting splits and merges in multi-person groups. Successful predictions should lead to more efficient planning while also increasing human acceptance of robot behavior. We take a novel approach by formulating this as a video prediction problem, where group splits or merges are predicted given a history of geometric social group shape transformations. We take inspiration from the success of 3D convolution models for video-related tasks. By treating the temporal dimension as a spatial dimension, a modified C3D model successfully captures the temporal features required to perform the prediction task. We demonstrate performance on several datasets and analyze transfer ability to other settings. While current approaches for tracking human motion are not explicitly designed for this task, our approach performs significantly better at predicting the occurrence of splits and merges. We also draw human interpretations from the model's learned features.

This research introduces a 6-degree-of-freedom parallel manipulator with a reconfigurable fixed base; the manipulator performance has been evaluated to select the most suitable reconfiguration system. The optimal design of the parallel manipulator refers to the enhancement of robot behavior achieved by the geometrical variation of the fixed platform. Motion/force transmission, with the aid of the principle of power conservation, defines the manipulator capacity to transmit its force from the actuated joints to the end-effector from different reconfiguration approaches and vice versa considering the stiffness analysis. Results allow inferring that reconfiguration of the fixed base enhances the performance of this parallel manipulator. The proposal of the reconfiguration system allows obtaining a reconfigurable parallel robot with the minimum number of actuators.

The paper is devoted to the study of problems on the behavior of finite automata in mazes. For any n, a maze is constructed that can be bypassed with 2n stones but you can’t get around with n stones. The range of tasks is extensive and touches upon key aspects of theoretical Computer Science. Of course, the solution of such problems does not mean the automatic solution of complex problems of complexity theory, however, the consideration of these issues can have a positive impact on the understanding of the essence of theoretical Computer Science. It is hoped that the behavior of automata in mazes is a good model for non-trivial information theoretic problems, and the development of methods and approaches to the study of robot behavior will give more serious results in the future. Problems related to automaton analysis of geometric media have a rather rich history of study. The first work that gave rise to this kind of problems, it is necessary to recognize the work of Shannon [24]. It deals with a model of a mouse in the form of an automaton, which must find a specific target in the maze. Another early work, one way or another affecting our problems, is the work of Fisher [9] on computing systems with external memory in the form of a discrete plane. A serious impetus to the study of the behavior of automata in mazes was the work of Depp [7, 8], in which the following model is proposed: there is a certain configuration of cells from mathbbZ^2 (chess maze), in which finite automata, surveying some neighborhood of the cell in which they are, can move to an adjacent cell in one of four directions. The main question posed in such a model is whether there is an automaton that bypasses all such mazes. In [20], Muller constructed a flat trap for a given automaton (a maze that does not completely bypass) in the form of a 3-graph. Budach [5] constructed a chess trap for any given finite automaton. Note that Budach’s solution was quite complex (the first versions contained 175 pages). More visual solutions to this question are presented here [29, 31, 33, 34]. Antelman [2] estimated the complexity of such a trap by the number of cells, and in [1] Antelman, Budach, and Rollick made a finite trap for any finite automaton system. In the formulation with a chess maze and one automaton, there are a number of results related to the problems of traversability of labyrinths with different numbers of holes, with bundles of labyrinths by the number of States of the automaton, and other issues. An overview of such problems can be found for example here [35]. The impossibility of traversing all flat chess labyrinths with one automaton raised the question of studying the possible amplifications of the automaton model, which will solve the problem of traversal. The main way of strengthening can be the consideration of a collective of automata, instead of one automaton, interacting with each other. A special and widely used case is the consideration of a system of one full-fledged automaton and a certain number of automata of stones, which have no internal state and can move only together with the main automaton. Interaction between machines is a key feature of this gain, it is allowed to have a collective (or one machine with stones) external memory, thereby significantly diversifies its behavior. If you get rid of the interaction of automata, the resulting independent system will be little better than a single machine. Next, we discuss the known results associated with the collective automata.

Modern emotional robots can support multimodal communicative interaction with humans through speech, hand gestures, head movements, eye and mouth animations. In the framework of this work, the contribution of individual active organs of the robot to the overall positive impression created by the robot in the user is investigated. The F-2 robot was used as an experimental platform. The experimental study revealed that users are significantly more likely to prefer a robot that uses gestures, head movements, eyes and mouth animation in its behavior compared to a robot in which the corresponding part of the body is stationary. The impact of robot’s eye movements on the user is not so clear: subjects significantly more often prefer a robot that uses eye movements in behavior, but they relatively rarely notice the difference between the two patterns of robot behavior – the behavior of the robot with fixed eyes and behavior of one with moving eyes.

Smart City aims to develop an environment in which different things goes to different people. The smart city provides a core infrastructure by improving the status of the inhabitants by providing a smart environment by applying Smart Solutions. The Internet of Things (IoT) is a revolutionary concept which finds its way in many applications such as business, industry, healthcare, Transportation, modern Information Technology applications and many more. IoT combined with Artificial Intelligence (AI) can be applied to many day to day applications in superior systems like transportation, robotics, industrial, and automation systems applications. This research focuses on developing a robotic behavior control using the Internet of Robotic Things (IoRT) using deep learning for a Smart City. The IoRT is a promising standard that brings together autonomous robotic systems in the midst of the IoT vision of connected sensors and smart objects pervasively embedded in the day to day environments. Robotic behavioral control models the robot with the essential features to react with the immediate environment via sensory-motor links. Robotic behavioral control has a direct interconnection between the sensors and actuators and controls the functions necessary to move around the environment and carry out necessary tasks. This deep learning solution applied to the robotic behavioral control for robotic application uses two main paradigms: Deep Reinforcement Learning (DRL) and Imitation Learning (IL).DRL merges the concept of deep learning architecture using neural networks and Reinforcement learning algorithms to identify the behavior of the robots.IL focus on imitating human learning or expert demonstration for controlling the robot behavior. The behavior of the robot is monitored in a diner and its performance is estimated to be 92% in realtime

To improve the safety and effectiveness of human-robot collaboration (HRC), the robot must plan a safe trajectory before the human movement is finished. Therefore, it is necessary to enable proactive robot behavior by making accurate intention prediction decisions early in a human motion. Furthermore, it is desirable to not only provide the long-term trajectory prediction of human motion but also characterize the uncertainty around it. In this paper, we present a human motion prediction framework to predict the motion trajectory of human arm in a reaching task. The proposed framework combines partial trajectory classification and human motion regression. By leveraging on the partial trajectory classification, our framework makes it possible to recognize the human action and to provide a trajectory prediction before the human movement is finished. The human motion regression can compensate the low accuracy of the representative trajectory through the fusion strategy. The proposed framework consists of two phases: online phase and offline phase. The offline phase aims to learn a regression model with optimized hyperparameters and a fusion strategy combining different prediction algorithms. In the online phase, based on the partial motion classification, the future reaching trajectory in a given time step is predicted by using a multi-step Gaussian process regression and representative trajectory. Experimental results show that our proposed framework achieved significant performance.

Summary: In addition to coding a subject’s location in space, the hippocampus has been suggested to code social information, including the spatial position of conspecifics. “Social place cells” have been reported for tasks in which an observer mimics the behavior of a demonstrator. We examine whether rat hippocampal neurons may encode the behavior of a minirobot, but without requiring the animal to mimic it. Rather than finding social place cells, we observe that robot behavioral patterns modulate place fields coding animal position. This modulation may be confounded by correlations between robot movement and changes in the animal’s position. Although rat position indeed significantly predicts robot behavior, we find that hippocampal ensembles code additional information about robot movement patterns. Fast-spiking interneurons are particularly informative about robot position and global behavior. In conclusion, when the animal’s own behavior is conditional on external agents, the hippocampus multiplexes information about self and others. : Bos et al. study hippocampal coding of an external agent’s location using a minirobot and find no evidence of mirror-like neurons coding location. They discover that CA1 firing patterns (especially interneurons) carry information about robot behavior and highlight the importance of controlling for confounds due to changes in animal position. Keywords: CA1, tetrode, place cells, social behavior, information theory, decoding, robot, place field, mutual information, interneuron

This paper presents a framework for programming in-contact tasks using learning by demonstration. The framework is demonstrated on an industrial gluing task, showing that a high quality robot behavior can be programmed using a single demonstration. A unified controller structure is proposed for the demonstration and execution of in-contact tasks that eases the transition from admittance controller for demonstration to parallel force/position control for the execution. The proposed controller is adapted according to the geometry of the task constraints, which is estimated online during the demonstration. In addition, the controller gains are adapted to the human behavior during demonstration to improve the quality of the demonstration. The considered gluing task requires the robot to alternate between free motion and in-contact motion; hence, an approach for minimizing contact forces during the switching between the two situations is presented. We evaluate our proposed system in a series of experiments, where we show that we are able to estimate the geometry of a curved surface, that our adaptive controller for demonstration allows users to achieve higher accuracy in a shorter demonstration duration when compared to an off-the-shelf controller for teaching implemented on a collaborative robot, and that our execution controller is able to reduce impact forces and apply a constant process force while adapting to the surface geometry.

Quantum computing offers a new approach to the problem modeling and solving. This paper deals with the quantum modeling of reactive agents. It also proposes a quantum algorithm to implement the subsumption architecture, widely used by reactive agents, particularly in robotics. This work shows the contribution of the formalism proposed by quantum mechanics to the modeling and the proof of certain properties of the agent behavior. After, the definition of the reactive agent state modeling, the paper suggests a behavior modeling approach based on two steps for subsumption architecture. The first one models the preset behavior that links each action to the perception states. The second one determines, among several actuated actions, the one that the robot must achieve. The subsumption architecture raises the challenge of modeling hierarchical priority of actions. To this end, a multipartite entanglement is used in the second step. More precisely, the paper proposes and generalizes a W-state circuit in order to be used for modeling hierarchical priority actions and controlling the robot accordingly. The result of both steps provides a formal model that links the robot’s perception (input) to the actions (output), with respect to the subsumption architecture. The proposed model of agent is simulated using IBM quantum computer. The simulation shows that the model can either be served as a control unit of the robot (CU) to obtain the suitable action or to simulate the robot behavior.

In human-robot collaboration (HRC), human trust in the robot is the human expectation that a robot executes tasks with desired performance. A higher-level trust increases the willingness of a human operator to assign tasks, share plans, and reduce the interruption during robot executions, thereby facilitating human-robot integration both physically and mentally. However, due to real-world disturbances, robots inevitably make mistakes, decreasing human trust and further influencing collaboration. Trust is fragile and trust loss is triggered easily when robots show incapability of task executions, making the trust maintenance challenging. To maintain human trust, in this research, a trust repair framework is developed based on a human-to-robot attention transfer (H2R-AT) model and a user trust study. The rationale of this framework is that a prompt mistake correction restores human trust. With H2R-AT, a robot localizes human verbal concerns and makes prompt mistake corrections to avoid task failures in an early stage and to finally improve human trust. User trust study measures trust status before and after the behavior corrections to quantify the trust loss. Robot experiments were designed to cover four typical mistakes, wrong action, wrong region, wrong pose, and wrong spatial relation, validated the accuracy of H2R-AT in robot behavior corrections; a user trust study with $252$ participants was conducted, and the changes in trust levels before and after corrections were evaluated. The effectiveness of the human trust repairing was evaluated by the mistake correction accuracy and the trust improvement., six pages

The incorporation of robots in the social fabric of our society has taken giant leaps, enabled by advances in artificial intelligence and big data. As these robots become increasingly adept at parsing through enormous datasets and making decisions where humans fall short, a significant challenge lies in the analysis of robot behavior. Capturing interactions between robots, humans and IoT devices in traditional structures such as graphs poses challenges in the storage and analysis of large data sets in dense graphs generated by frequent activities. This paper proposes a framework that uses the blockchain for the storage of robotic interactions, and the use of sheaf theory for analysis of these interactions. Further, the use of smart contracts on the blockchain is proposed with an embedding of two parameters in the smart contracts – imperfect information and irrationality – to enable robots to operate deftly in various human environments that expect different levels of dominance from the robot. This work shows the application of such a framework for various blockchain applications on the spectrum of human-robot interaction, and identifies key challenges that arise as a result of using the blockchain for robotic applications.

Cooperative physical Human Robot Interaction (pHRI) aims to combine the best of human problem-solving skills with the strength, speed and accuracy of a robot. When humans and robots physically interact, there will be interaction Forces and Torques (F/Ts) that must be within safe limits to avoid threats to human life and unacceptable damage to equipment. When measured, these F/Ts can be limited by safety rated emergency stops, and one can design a compliant robot behavior to reduce interaction F/Ts, and avoid unnecessary emergency stops. Several recent collaborative robots offer measurements of interaction F/Ts by utilizing torque sensors in joints or observers for joint torque, and the classical end-effector F/T sensor can provide measurements of interaction at the working end of a robot. The end-effector wrench can be calculated from joint torques if and only if there is no interaction on the robot body. Typically, safety limits are evaluated around a single point of contact – on the end-effector or elsewhere on the robot body. This approach fails when a human uses both hands to interact with a robot, e.g. when hand guiding or otherwise cooperating with the robot placing one hand on the robot end-effector and the other hand on the robot elbow. Having two points of contact that are evaluated as one will limit the allowed F/Ts of the sum of the contacts rather than individually. In this paper, we introduce the body torque as the interaction on the body that is not the result of interactions on the end-effector. We then use this body torque, which is a more accurate representation of the forces applied to the robot body, to limit the body interaction F/Ts to ensure safe human-robot interaction. Furthermore, the body torque can be used to design null-space compliance for a redundant robot. Distinguishing body torque is a step towards safe cooperative pHRI, where body torque, unknown end-effector loads, and end-effector interaction F/T are all important measurements for safety, control and compliance.

International audience; Assessing robotic architecture for Human-Robot Interaction can be challenging due to the number of features a robot has to endow to perform an acceptable interaction. While everyday-inspired tasks are interesting as reflecting a realistic use of such robots, they often contain a lot of unknown and uncontrolled conditions and specific robot behavior can be hard to test. In this paper, we propose a new psychology-inspired task, gathering perspective-taking, planning, knowledge representation with theory of mind, manipulation, and communication. Along with a precise description of the task allowing its replication, we present a cognitive robot architecture able to perform it in its nominal cases. We finally suggest some challenges and evaluations for the Human-Robot Interaction research community, all derived from this easy-to-replicate task.

Reinforcement learning is inherently unsafe for use in physical systems, as learning by trial-and-error can cause harm to the environment or the robot itself. One way to avoid unpredictable exploration is to add constraints in the action space to restrict the robot behavior. In this paper, we proposea null space based framework of integrating reinforcement learning methods in constrained continuous action spaces. We leverage a hierarchical control framework to decompose target robotic skills into higher ranked tasks (e. g., joint limits and obstacle avoidance) and lower ranked reinforcement learning task. Safe exploration is guaranteed by only learning policies in the null space of higher prioritized constraints. Meanwhile multiple constraint phases for different operational spaces are constructed to guide the robot exploration. Also, we add penalty loss for violating higher ranked constraints to accelerate the learning procedure. We have evaluated our method on different redundant robotic tasks in simulation and show that our null space based reinforcement learning method can explore and learn safely and efficiently., Funding agency:Wallenberg Artificial Intelligence, Autonomous Systems and Software Program (WASP)

This paper focuses on a 4-mecanum wheeled mobile robot used for transportation tasks in manufacturing industry. It aims to supervise the health state of the robot actuators after a first detection of faults, and to study the faults impact on the robot behavior. As faults are considered the loss of actuators efficiency due to wear linked to the robot high solicitation. The main contribution is on the one hand the diagnosis of simultaneous actuator faults and on the other hand the impact study of these faults on the robot behavior to determine degradation limits which guarantee that the robot is still close to the desired performance. The objective is to provide to the user a decision-making support regarding whether (or not) the robot is still able to continue functioning with respect to security instructions imposed by its environment. Two main cases are dealt: 1) All the four-actuators lose from 0% (no fault) to 95% of their efficiency. 2) One actuator is completely defective (it loses 100 % of its efficiency), while the three-others lose from 0% to 95% of their efficiency. Different scenarios are tested to analyze the impact of the robot missions and the working conditions on its behavior under degradation.

Motion-controlled robotic systems would become more and more popular in the future since they allow humans to easily control robots to carry out various tasks. However, current authentication methods rely on static credentials, such as passwords, fingerprints, and faces, which are independent of the robot control. Thus, they cannot guarantee that a robot is always under the control of its enrolled user. In this paper, we build a motion-controlled robotic arm system and show that a robotic arm’s motion inherits much of its user’s behavioral information in interactive control scenarios. Based on that, we propose a novel user authentication approach to verify the robotic arm user. In particular, we log the angle readings of the robotic arm’s joints to reconstruct the 3D movement trajectory of its end effector. We then develop a learning-based algorithm to identify the user. Extensive experiments show that our system achieves 95% accuracy to verify users while preventing various impersonation attacks.

We study the problem of learning a formal representation of a robot's social obligations from a human population's preferences. Rigorous system design requires a logical formalization of a robot's desired behavior, including the social obligations that constrain its actions. The preferences of the society hosting these robots are a natural source of these obligations. Thus we ask: how can we turn a popu-lation's preferences concerning robot behavior into a logico-mathematical specification that we can use to design the robot's controllers? We use non-deterministic weighted automata to model a robot's behavioral algorithms, and we use the deontic logic of Dominance Act Utilitarianism (DAU) to model the robot's social and ethical obligations. Given a set of automaton executions, and pair-wise comparisons between the executions, we develop simple algorithms to infer the automaton's weights, and compare them to existing methods; these weights are then turned into logical obligation formulas in DAU. We bound the sensitivity of the inferred weights to changes in the comparisons. We evaluate empirically the degree to which the obligations inferred from these various methods differ from each other.

A longstanding barrier to deploying robots in the real world is the ongoing need to author robot behavior. Remote data collection–particularly crowdsourcing—is increasingly receiving interest. In this paper, we make the argument to scale robot programming to the crowd and present an initial investigation of the feasibility of this proposed method. Using an off-the-shelf visual programming interface, non-experts created simple robot programs for two typical robot tasks (navigation and pick-and-place). Each needed four subtasks with an increasing number of programming statements (if statement, while loop, variables) for successful completion of the programs. Initial findings of an online study (N = 279) indicate that non-experts, after minimal instruction, were able to create simple programs using an off-the-shelf visual programming interface. We discuss our findings and identify future avenues for this line of research.

Genetic encodings and their particular properties are known to have a strong influence on the success of evolutionary systems. However, the literature has widely focused on studying the effects that encodings have on performance, i.e., fitness-oriented studies. Notably, this anchoring of the literature to performance is limiting, considering that performance provides bounded information about the behavior of a robot system. In this paper, we investigate how genetic encodings constrain the space of robot phenotypes and robot behavior. In summary, we demonstrate how two generative encodings of different nature lead to very different robots and discuss these differences. Our principal contributions are creating awareness about robot encoding biases, demonstrating how such biases affect evolved morphological, control, and behavioral traits, and finally scrutinizing the trade-offs among different biases.

Continuum robots are a type of robotic device that are characterized by their flexibility and dexterity, thus making them ideal for an active endoscope. Instead of articulated joints they have flexible backbones that can be manipulated remotely, usually through tendons secured onto structures attached to the backbone. This structure makes them lightweight and ideal to be miniaturized for endoscopic applications. However, their flexibility poses technical challenges in the modeling and control of these devices, especially when closed-loop control is needed, as is the case in medical applications. There are two main approaches in the modeling of continuum robots, the first is to theoretically model the behavior of the backbone and the interaction with the tendons, while the second is to collect experimental observations and retrospectively apply a model that can approximate their apparent behavior. Both approaches are affected by the complexity of continuum robots through either model accuracy/computational time (theoretical method) or missing complex system interactions and lacking expandability (experimental method). In this work, theoretical and experimental descriptions of an endoscopic continuum robot are merged. A simplified yet representative mathematical model of a continuum robot is developed, in which the backbone model is based on Cosserat rod theory and is coupled to the tendon tensions. A robust numerical technique is formulated that has low computational costs. A bespoke experimental facility with precise automated motion of the backbone via the precise control of tendon tension, leads to a robust and detailed description of the system behavior provided through a contactless sensor. The resulting facility achieves a real-world mean positioning error of 3.95% of the backbone length for the examined range of tendon tensions which performs favourably to existing approaches. Moreover, it incorporates hysteresis behavior that could not be predicted by the theoretical modeling alone, reinforcing the benefits of the hybrid approach. The proposed workflow is theoretically grounded and experimentally validated allowing precise prediction of the continuum robot behavior, adhering to realistic observations. Based on this accurate estimation and the fact it is geometrically agnostic enables the proposed model to be scaled for various robotic endoscopes.