Search

Nature has demonstrated an incredible ability to optimize the designs and behaviors of humans, animals, and plants. Many areas of engineering have tried to copy the optimality principles of nature or optimize technical properties of systems, and mathematical optimization has been a very helpful tool in this context. To promote the use of optimization methods in robotics, the IEEE Robotics and Automation Society (RAS) Technical Committee (TC) on Model-Based Optimization for Robotics was founded and approved by the IEEE RAS Technical Activities Board and the RAS Administrative Committee in October 2012 with Cochairs Katja Mombaur, Abderrahmane Kheddar, Kensuke Harada, Thomas Buschmann, and Chris Atkeson. The TC focuses on optimization in robotics in the very general sense and, in particular, on the development and application of optimization methods for the design of robots and the generation and control of dynamic behaviors in robotics as well as their practical implementation. Optimization approaches are, in principle, applicable to any type of robot or robot behavior but are most interesting for robots with complex structures and dynamics, e.g., humanoid robots, or for high speeds, e.g., in mobile or agile manipulation (Figures 1–3). Optimization problems in robotics range from different tasks related to model identification (such as parameter estimation, optimum experimental design, inverse optimal control, and so on) over design optimization to optimal behavior generation (offline optimal control, model predictive control/online optimal control). Recent developments in optimization algorithms and, in particular, real-time optimization make a wider application of algorithmic optimization a realistic option even for real-time control in complex robotic applications in the near future. There is a growing interest in optimization in the robotics community for behavior generation and control, as recent publications and workshops show. However, it can be observed that the level of optimization techniques used is often far behind the current state of the art within the optimization community and that only very simple optimization problems are solved. This prevents the optimization potential of existing robot platforms from being fully exploited, and current designs are often suboptimal. But some papers show very interesting optimization solutions for the most advanced robotic systems, even for complex tasks with impacts or varying constraints, such as weight lifting or fast walking. At the same time, it is still a major challenge to actually apply these optimal solutions robustly to real robots and to handle modeling errors and uncertainties. Important research areas in the scope of this TC include: ● the optimization-based generation of robot trajectories using dynamical models of the robot and its environment ● improving the behavior style of robots by optimization, in particular for humanoid robots (induce natural behavior) ● online motion control using realtime model-based optimization and model predictive control/receding horizon control ● optimizing the design of robots for given tasks (parameter optimization and structural optimization) ● the development of appropriate dynamical models for offline and online optimization ● learning/improving models during optimization ● inverse optimal control techniques for the identification of objective functions ● robust optimal control and the refinement of optimal control policies based on actual experience ● the combination of optimization and machine-learning approaches ● the combination of optimization and path-planning methods.

In this paper, we present our current research on developing a model of robot behavior that leads to feelings of “being together” using the robot's body position and orientation. Creating feelings of “being together” will be an essential skill for robots that live with humans and adapt to daily human activities such as walking together or establishing joint attention to information in the environment. We observe people's proxemic behavior in joint attention situations and develop a model of behavior for robots to detect a partner's attention shift and appropriately adjust its body position and orientation in establishing joint attention with the partner. We experimentally evaluate the effectiveness of our model, and our results demonstrate the model's effectiveness.

This paper proposes a method to design the layers of Subsumption Architeture as objects. In this architecture, layers communicate with each other by wires. Generally, it is very difficult to design a connection of wires that enable a robot behave as we intend to. In this architecture, bugs in lower layers are assumed to be fixed, so it is possible to pile up upper layers on the lower layers. However, this connection of complicated wires, so-called a“spaghetti structure” makethe bug fix difficult. While if we design layers independently without wires, although the bug fix becomes easier, it is obviously difficult to make a robot behave as we intend to. Therefore, we propose a method to design object-oriented modules and layered structures of Subsumption Architeture. With this method, not only the bug fix becomes easier but also enable a robot execute planned tasks. In this paper, we apply this method to navigation tasks and show simulations and experimental results of it.

But for me, these questions are much too big for one person’s life pursuit. I like knowing the answer to problems, and these questions are too complex to be answered easily. Instead, what if we study a “simpler” life form – a robot – and try to answer these questions in that context? How can we give robots the capability to solve problems in a way that is as “natural” for the robot as it seems to be for us as humans? And, why not develop these answers by applying robots to real-world problems that can help make our complex human lives a bit easier (and perhaps even more interesting)? Then, we can have answers to these fascinating questions while at the same time applying our work to benefit human society. To me, this is a great motivation for my research in artificial intelligence and autonomous robotics, and what makes this work very satisfying to me.

The objective of this work is to develop a new robot intelligence for human-machine communication and environment-machine interaction based on the self-preservation function which should be involved in human mind. In this paper, the system chart expressing the human brain information processing, and the development of an autonomous mobile robot “WAMOEBA-1R” (Waseda Artificial Mind On Emotion BAse) are described. The concept of the WAMOEBA-1R design is that robots should have Self-Preservation Evaluation Function as an emotion function. Further more, the method to evaluate the whole system are described from the viewpoint of the animal psychology. As a result of the experiments, WAMOEBA-1R showed specific reactions with color emotion appearances to some simulations. WAMOEBA-1R had the sense of values about colors and sounds based on Self-Preservation, and achieved new type human-machine communications by expressing an emotion color.

This paper describes a software framework which can support different types of bodies and behaviors with different processing times. The system we propose consists of 3 parts, “Mother, Brain, Sensor & Actuator”. Brain consists of robot behavior programs and their supporting libraries, and Sensor & Actuator consists of sensor processing and actuator control system. Mother consists of tools to produce and evolve Brain programs.In building tools and libraries for such a platform you are faced with two major problems. One is, system architecture will always have a trade-off relationship with “extensibility” and “shareablity” . The other problem you encounter is the difference in execution time between the low-level real-time reactive environment and the high-level behavioral software.In this paper we describe the methods and the software environment that we built which overcomes the problems mentioned above, based on the remote-brained robotic approach. This system enables us to develop flexible multiprocess networks made of processes with differing computing times which in turn enables the contruction of various brain architectures.

This paper examines feasibility of a space robot system which captures a free-flying target. First, to examine it experimentally, we develop a berthing dynamics simulator (BDS) on which the space robot and the target behave as if they were on orbit. BDS measures force and torque operating on the real hardware, and it calculates the motion of the robot and the target using the detected force, then it drives the servo mechanisms so that they conform to the calculated posture. Next, to examine the feasibility by use of only numerical simulation, we propose a mathematical model. The validity of the model is verified in comparison with the experiments performed on BDS. Finally, it is confirmed that the space robot can automatically capture the free-flying target without yielding excessive force and oscillation by the experiments and the numerical simulation.

The mobile robot wil meet various situations while it moves in the real environment. The occurrence of such situations are caused by the uncertainty of the real environment, and it's impossible to determine the exact timing of the occurrence before robot's moving. Therefore, the mobile robot must watch environment by its sensors and change its motion dynamically dealing with the occurred situations.In this paper, the concept of Action mode is introduced to analyze and represent such behavior of the mobile robot. Action mode is defined by motion commands to the actuator controller, the conditions to watch various situations and motion selection to deal with occurred situations. The robot behavior is represented by transition of Action modes. The robot control language ROBOL/0 based on the Action mode representation is proposed. The navigation of a mobile robot in the real world using the sensor and map information is treated as an example.