Search

Cross-embodiment imitation learning enables policies trained on specific embodiments to transfer across different robots, unlocking the potential for large-scale imitation learning that is both cost-effective and highly reusable. This paper presents LEGATO, a cross-embodiment imitation learning framework for visuomotor skill transfer across varied kinematic morphologies. We introduce a handheld gripper that unifies action and observation spaces, allowing tasks to be defined consistently across robots. Using this gripper, we train visuomotor policies via imitation learning, applying a motion-invariant transformation to compute the training loss. Gripper motions are then retargeted into high-degree-of-freedom whole-body motions using inverse kinematics for deployment across diverse embodiments. Our evaluations in simulation and real-robot experiments highlight the framework's effectiveness in learning and transferring visuomotor skills across various robots. More information can be found at the project page: https://ut-hcrl.github.io/LEGATO., Comment: Submitted to RA-L

Wildfire suppression is a complex task that poses high risks to humans. Using robotic teams for wildfire suppression enhances the safety and efficiency of detecting, monitoring, and extinguishing fires. We propose a control architecture based on task hierarchical control for the autonomous steering of a system of flying robots in wildfire suppression. We incorporate a novel line-of-sight obstacle avoidance method that calculates the best viewpoints and ensures an occlusion-free view for the suppression robot during the mission. Path integral control generates optimal trajectories towards the goals. We conduct an ablation study to assess the effectiveness of our approach by comparing it to scenarios where these key components are excluded, in order to validate the approach in simulations using Matlab and Unity. The results demonstrate significant performance improvements, with 44.0 % increase in effectiveness with the new line-of-sight obstacle avoidance task and up to 39.6 % improvement when using path integral control., Comment: 6 pages, 5 figures, submitted to joint ACC and L-CSS

Humanoid robots rely on multi-contact planners to navigate a diverse set of environments, including those that are unstructured and highly constrained. To synthesize stable multi-contact plans within a reasonable time frame, most planners assume statically stable motions or rely on reduced order models. However, these approaches can also render the problem infeasible in the presence of large obstacles or when operating near kinematic and dynamic limits. To that end, we propose a new multi-contact framework that leverages recent advancements in relaxing collision-free path planning into a convex optimization problem, extending it to be applicable to humanoid multi-contact navigation. Our approach generates near-feasible trajectories used as guides in a dynamic trajectory optimizer, altogether addressing the aforementioned limitations. We evaluate our computational approach showcasing three different-sized humanoid robots traversing a high-raised naval knee-knocker door using our proposed framework in simulation. Our approach can generate motion plans within a few seconds consisting of several multi-contact states, including dynamic feasibility in joint space., Comment: Accepted for publication in IEEE-RAS International Conference of Humanoid Robots (Humanoids 2024)

This paper presents an open-source, lightweight, yet comprehensive software framework, named RPC, which integrates physics-based simulators, planning and control libraries, debugging tools, and a user-friendly operator interface. RPC enables users to thoroughly evaluate and develop control algorithms for robotic systems. While existing software frameworks provide some of these capabilities, integrating them into a cohesive system can be challenging and cumbersome. To overcome this challenge, we have modularized each component in RPC to ensure easy and seamless integration or replacement with new modules. Additionally, our framework currently supports a variety of model-based planning and control algorithms for robotic manipulators and legged robots, alongside essential debugging tools, making it easier for users to design and execute complex robotics tasks. The code and usage instructions of RPC are available at https://github.com/shbang91/rpc., Comment: 7pages, 4 figures

This paper presents a set of simple and intuitive robot collision detection algorithms that show substantial scaling improvements for high geometric complexity and large numbers of collision queries by leveraging hardware-accelerated ray tracing on GPUs. It is the first leveraging hardware-accelerated ray-tracing for direct volume mesh-to-mesh discrete collision detection and applying it to continuous collision detection. We introduce two methods: Ray-Traced Discrete-Pose Collision Detection for exact robot mesh to obstacle mesh collision detection, and Ray-Traced Continuous Collision Detection for robot sphere representation to obstacle mesh swept collision detection, using piecewise-linear or quadratic B-splines. For robot link meshes totaling 24k triangles and obstacle meshes of over 190k triangles, our methods were up to 3 times faster in batched discrete-pose queries than a state-of-the-art GPU-based method using a sphere robot representation. For the same obstacle mesh scene, our sphere-robot continuous collision detection was up to 9 times faster depending on trajectory batch size. We also performed a detailed measurement of the volume coverage accuracy of various sphere/mesh pose/path representations to provide insight into the tradeoffs between speed and accuracy of different robot collision detection methods.

Multi-suction-cup grippers are frequently employed to perform pick-and-place robotic tasks, especially in industrial settings where grasping a wide range of light to heavy objects in limited amounts of time is a common requirement. However, most existing works focus on using one or two suction cups to grasp only irregularly shaped but light objects. There is a lack of research on robust manipulation of heavy objects using larger arrays of suction cups, which introduces challenges in modeling and predicting grasp failure. This paper presents a general approach to modeling grasp strength in multi-suction-cup grippers, introducing new constraints usable for trajectory planning and optimization to achieve fast and reliable pick-and-place maneuvers. The primary modeling challenge is the accurate prediction of the distribution of loads at each suction cup while grasping objects. To solve for this load distribution, we find minimum spring potential energy configurations through a simple quadratic program. This results in a computationally efficient analytical solution that can be integrated to formulate grasp failure constraints in time-optimal trajectory planning. Finally, we present experimental results to validate the efficiency and accuracy of the proposed model.

This paper proposes an online bipedal footstep planning strategy that combines model predictive control (MPC) and reinforcement learning (RL) to achieve agile and robust bipedal maneuvers. While MPC-based foot placement controllers have demonstrated their effectiveness in achieving dynamic locomotion, their performance is often limited by the use of simplified models and assumptions. To address this challenge, we develop a novel foot placement controller that leverages a learned policy to bridge the gap between the use of a simplified model and the more complex full-order robot system. Specifically, our approach employs a unique combination of an ALIP-based MPC foot placement controller for sub-optimal footstep planning and the learned policy for refining footstep adjustments, enabling the resulting footstep policy to capture the robot's whole-body dynamics effectively. This integration synergizes the predictive capability of MPC with the flexibility and adaptability of RL. We validate the effectiveness of our framework through a series of experiments using the full-body humanoid robot DRACO 3. The results demonstrate significant improvements in dynamic locomotion performance, including better tracking of a wide range of walking speeds, enabling reliable turning and traversing challenging terrains while preserving the robustness and stability of the walking gaits compared to the baseline ALIP-based MPC approach., Comment: 8 pages, 7 figures

This paper proposes a novel control framework for agile and robust bipedal locomotion, addressing model discrepancies between full-body and reduced-order models. Specifically, assumptions such as constant centroidal inertia have introduced significant challenges and limitations in locomotion tasks. To enhance the agility and versatility of full-body humanoid robots, we formalize a Model Predictive Control (MPC) problem that accounts for the variable centroidal inertia of humanoid robots within a convex optimization framework, ensuring computational efficiency for real-time operations. In the proposed formulation, we incorporate a centroidal inertia network designed to predict the variable centroidal inertia over the MPC horizon, taking into account the swing foot trajectories -- an aspect often overlooked in ROM-based MPC frameworks. By integrating the MPC-based contact wrench planning with our low-level whole-body controller, we significantly improve the locomotion performance, achieving stable walking at higher velocities that are not attainable with the baseline method. The effectiveness of our proposed framework is validated through high-fidelity simulations using our full-body bipedal humanoid robot DRACO 3, demonstrating dynamic behaviors., Comment: 8pages, 6figures

This paper introduces quantum edge detection, aimed at locating boundaries of quantum domains where all particles share the same pure state. Focusing on the 1D scenario of a string of particles, we develop an optimal protocol for quantum edge detection, efficiently computing its success probability through Schur-Weyl duality and semidefinite programming techniques. We analyze the behavior of the success probability as a function of the string length and local dimension, with emphasis in the limit of long strings. We present a protocol based on square root measurement, which proves asymptotically optimal. Additionally, we explore a mixed quantum change point detection scenario where the state of particles transitions from known to unknown, which may find practical applications in detecting malfunctions in quantum devices, Comment: 13+6 pages, 2 figures

Jerk-constrained trajectories offer a wide range of advantages that collectively improve the performance of robotic systems, including increased energy efficiency, durability, and safety. In this paper, we present a novel approach to jerk-constrained time-optimal trajectory planning (TOTP), which follows a specified path while satisfying up to third-order constraints to ensure safety and smooth motion. One significant challenge in jerk-constrained TOTP is a non-convex formulation arising from the inclusion of third-order constraints. Approximating inequality constraints can be particularly challenging because the resulting solutions may violate the actual constraints. We address this problem by leveraging convexity within the proposed formulation to form conservative inequality constraints. We then obtain the desired trajectories by solving an $\boldsymbol n$-dimensional Sequential Linear Program (SLP) iteratively until convergence. Lastly, we evaluate in a real robot the performance of trajectories generated with and without jerk limits in terms of peak power, torque efficiency, and tracking capability.

Despite the rise of mobile robot deployments in home and work settings, perceived safety of users and bystanders is understudied in the human-robot interaction (HRI) literature. To address this, we present a study designed to identify elements of a human-robot encounter that correlate with observed stress response. Stress is a key component of perceived safety and is strongly associated with human physiological response. In this study a Boston Dynamics Spot and a Unitree Go1 navigate autonomously through a shared environment occupied by human participants wearing multimodal physiological sensors to track their electrocardiography (ECG) and electrodermal activity (EDA). The encounters are varied through several trials and participants self-rate their stress levels after each encounter. The study resulted in a multidimensional dataset archiving various objective and subjective aspects of a human-robot encounter, containing insights for understanding perceived safety in such encounters. To this end, acute stress responses were decoded from the human participants' ECG and EDA and compared across different human-robot encounter conditions. Statistical analysis of data indicate that on average (1) participants feel more stress during encounters compared to baselines, (2) participants feel more stress encountering multiple robots compared to a single robot and (3) participants stress increases during navigation behavior compared with search behavior., Comment: 8 pages, 7 figs, 5 tables

A source assumed to prepare a specified reference state sometimes prepares an anomalous one. We address the task of identifying these anomalous states in a series of $n$ preparations with $k$ anomalies. We analyze the minimum-error protocol and the zero-error (unambiguous) protocol and obtain closed expressions for the success probability when both reference and anomalous states are known to the observer and anomalies can appear equally likely in any position of the preparation series. We find the solution using results from association schemes theory, thus establishing a connection between graph theory and quantum hypothesis testing. In particular, we use the Johnson association scheme which arises naturally from the Gram matrix of this problem. We also study the regime of large $n$ and obtain the expression of the success probability that is non-vanishing. Finally, we address the case in which the observer is blind to the reference and the anomalous states. This scenario requires a universal protocol for which we prove that in the asymptotic limit, the success probability corresponds to the average of the known state scenario., Comment: 9 pages, 4 figures

This paper introduces LIVE: Lidar Informed Visual Search focused on the problem of multi-robot (MR) planning and execution for robust visual detection of multiple objects. We perform extensive real-world experiments with a two-robot team in an indoor apartment setting. LIVE acts as a perception module that detects unmapped obstacles, or Short Term Features (STFs), in Lidar observations. STFs are filtered, resulting in regions to be visually inspected by modifying plans online. Lidar Coverage Path Planning (CPP) is employed for generating highly efficient global plans for heterogeneous robot teams. Finally, we present a data model and a demonstration dataset, which can be found by visiting our project website https://sites.google.com/view/live-iros2023/home., Comment: 4 pages + references; 6 figures

This paper details a system for fast visual exploration and search without prior map information. We leverage frontier based planning with both LiDAR and visual sensing and augment it with a perception module that contextually labels points in the surroundings from wide Field of View 2D LiDAR scans. The goal of the perception module is to recognize surrounding points more likely to be the search target in order to provide an informed prior on which to plan next best viewpoints. The robust map-free scan classifier used to label pixels in the robot's surroundings is trained from expert data collected using a simple cart platform equipped with a map-based classifier. We propose a novel utility function that accounts for the contextual data found from the classifier. The resulting viewpoints encourage the robot to explore points unlikely to be permanent in the environment, leading the robot to locate objects of interest faster than several existing baseline algorithms. Our proposed system is further validated in real-world search experiments for single and multiple search objects with a Spot robot in two unseen environments. Videos of experiments, implementation details and open source code can be found at https://sites.google.com/view/lives-2024/home., Comment: 7 pages. 9 figures. 1 algorithm. 1 table

In this paper, we address the challenge of deriving dynamical models from sparse and noisy data. High-quality data is crucial for symbolic regression algorithms; limited and noisy data can present modeling challenges. To overcome this, we combine Gaussian process regression with a sparse identification of nonlinear dynamics (SINDy) method to denoise the data and identify nonlinear dynamical equations. Our approach GPSINDy offers improved robustness with sparse, noisy data compared to SINDy alone. We demonstrate its effectiveness on simulation data from Lotka-Volterra and unicycle models and hardware data from an NVIDIA JetRacer system. We show superior performance over baselines including more than 50% improvement over SINDy and other baselines in predicting future trajectories from noise-corrupted and sparse 5 Hz data., Comment: Submitted to ACC 2025

We tackle the problem of developing humanoid loco-manipulation skills with deep imitation learning. The difficulty of collecting task demonstrations and training policies for humanoids with a high degree of freedom presents substantial challenges. We introduce TRILL, a data-efficient framework for training humanoid loco-manipulation policies from human demonstrations. In this framework, we collect human demonstration data through an intuitive Virtual Reality (VR) interface. We employ the whole-body control formulation to transform task-space commands by human operators into the robot's joint-torque actuation while stabilizing its dynamics. By employing high-level action abstractions tailored for humanoid loco-manipulation, our method can efficiently learn complex sensorimotor skills. We demonstrate the effectiveness of TRILL in simulation and on a real-world robot for performing various loco-manipulation tasks. Videos and additional materials can be found on the project page: https://ut-austin-rpl.github.io/TRILL., Comment: Accepted to Humanoids 2023

The quantum state associated to an unknown experimental preparation procedure can be determined by performing quantum state tomography. If the statistical uncertainty in the data dominates over other experimental errors, then a tomographic reconstruction procedure must express this uncertainty. A rigorous way to accomplish this is via statistical confidence regions in state space. Naturally, the size of this region decreases when increasing the number of samples, but it also depends critically on the construction method of the region. We compare recent methods for constructing confidence regions as well as a reference method based on a Gaussian approximation. For the comparison, we propose an operational measure with the finding, that there is a significant difference between methods, but which method is preferable can depend on the details of the state preparation scenario., Comment: 20 pages, 4 figures

Navigation strategies that intentionally incorporate contact with humans (i.e. "contact-based" social navigation) in crowded environments are largely unexplored even though collision-free social navigation is a well studied problem. Traditional social navigation frameworks require the robot to stop suddenly or "freeze" whenever a collision is imminent. This paradigm poses two problems: 1) freezing while navigating a crowd may cause people to trip and fall over the robot, resulting in more harm than the collision itself, and 2) in very dense social environments where collisions are unavoidable, such a control scheme would render the robot unable to move and preclude the opportunity to study how humans incorporate robots into these environments. However, if robots are to be meaningfully included in crowded social spaces, such as busy streets, subways, stores, or other densely populated locales, there may not exist trajectories that can guarantee zero collisions. Thus, adoption of robots in these environments requires the development of minimally disruptive navigation plans that can safely plan for and respond to contacts. We propose a learning-based motion planner and control scheme to navigate dense social environments using safe contacts for an omnidirectional mobile robot. The planner is evaluated in simulation over 360 trials with crowd densities varying between 0.0 and 1.6 people per square meter. Our navigation scheme is able to use contact to safely navigate in crowds of higher density than has been previously reported, to our knowledge., Comment: Presented at the Human Interactive Robot Learning worksop at HRI2023

Operating quantum sensors and quantum computers would make data in the form of quantum states available for purely quantum processing, opening new avenues for studying physical processes and certifying quantum technologies. In this Perspective, we review a line of works dealing with measurements that reveal structural properties of quantum datasets given in the form of product states. These algorithms are universal, meaning that their performances do not depend on the reference frame in which the dataset is provided. Requiring the universality property implies a characterization of optimal measurements via group representation theory.

Model generalization of the underlying dynamics is critical for achieving data efficiency when learning for robot control. This paper proposes a novel approach for learning dynamics leveraging the symmetry in the underlying robotic system, which allows for robust extrapolation from fewer samples. Existing frameworks that represent all data in vector space fail to consider the structured information of the robot, such as leg symmetry, rotational symmetry, and physics invariance. As a result, these schemes require vast amounts of training data to learn the system's redundant elements because they are learned independently. Instead, we propose considering the geometric prior by representing the system in symmetrical object groups and designing neural network architecture to assess invariance and equivariance between the objects. Finally, we demonstrate the effectiveness of our approach by comparing the generalization to unseen data of the proposed model and the existing models. We also implement a controller of a climbing robot based on learned inverse dynamics models. The results show that our method generates accurate control inputs that help the robot reach the desired state while requiring less training data than existing methods.

In this paper, we introduce the humanoid robot DRACO 3 by providing a high-level description of its design and control. This robot features proximal actuation and mechanical artifacts to provide a high range of hip, knee and ankle motion. Its versatile design brings interesting problems as it requires a more elaborate control system to perform its motions. For this reason, we introduce a whole body controller (WBC) with support for rolling contact joints and show how it can be easily integrated into our previously presented open-source Planning and Control (PnC) framework. We then validate our controller experimentally on DRACO 3 by showing preliminary results carrying out two postural tasks. Lastly, we analyze the impact of the proximal actuation design and show where it stands in comparison to other adult-size humanoids.

This paper proposes a real-time model predictive control (MPC) scheme to execute multiple tasks using robots over a finite-time horizon. In industrial robotic applications, we must carefully consider multiple constraints for avoiding joint position, velocity, and torque limits. In addition, singularity-free and smooth motions require executing tasks continuously and safely. Instead of formulating nonlinear MPC problems, we devise linear MPC problems using kinematic and dynamic models linearized along nominal trajectories produced by hierarchical controllers. These linear MPC problems are solvable via the use of Quadratic Programming; therefore, we significantly reduce the computation time of the proposed MPC framework so the resulting update frequency is higher than 1 kHz. Our proposed MPC framework is more efficient in reducing task tracking errors than a baseline based on operational space control (OSC). We validate our approach in numerical simulations and in real experiments using an industrial manipulator. More specifically, we deploy our method in two practical scenarios for robotic logistics: 1) controlling a robot carrying heavy payloads while accounting for torque limits, and 2) controlling the end-effector while avoiding singularities., Comment: 7 pages, 6 figures

We tackle the problem of perceptive locomotion in dynamic environments. In this problem, a quadrupedal robot must exhibit robust and agile walking behaviors in response to environmental clutter and moving obstacles. We present a hierarchical learning framework, named PRELUDE, which decomposes the problem of perceptive locomotion into high-level decision-making to predict navigation commands and low-level gait generation to realize the target commands. In this framework, we train the high-level navigation controller with imitation learning on human demonstrations collected on a steerable cart and the low-level gait controller with reinforcement learning (RL). Therefore, our method can acquire complex navigation behaviors from human supervision and discover versatile gaits from trial and error. We demonstrate the effectiveness of our approach in simulation and with hardware experiments. Videos and code can be found at the project page: https://ut-austin-rpl.github.io/PRELUDE., Comment: Accepted to ICRA 2023

This paper proposes KC-TSS: K-Clustered-Traveling Salesman Based Search, a failure resilient path planning algorithm for heterogeneous robot teams performing target search in human environments. We separate the sample path generation problem into Heterogeneous Clustering and multiple Traveling Salesman Problems. This allows us to provide high-quality candidate paths (i.e. minimal backtracking, overlap) to an Information-Theoretic utility function for each agent. First, we generate waypoint candidates from map knowledge and a target prediction model. All of these candidates are clustered according to the number of agents and their ability to cover space, or coverage competency. Each agent solves a Traveling Salesman Problem (TSP) instance over their assigned cluster and then candidates are fed to a utility function for path selection. We perform extensive Gazebo simulations and preliminary deployment of real robots in indoor search and simulated rescue scenarios with static targets. We compare our proposed method against a state-of-the-art algorithm and show that ours is able to outperform it in mission time. Our method provides resilience in the event of single or multi teammate failure by recomputing global team plans online.

Planning safe motions for legged robots requires sophisticated safety verification tools. However, designing such tools for such complex systems is challenging due to the nonlinear and high-dimensional nature of these systems' dynamics. In this letter, we present a probabilistic verification framework for legged systems, which evaluates the safety of planned trajectories by learning an assessment function from trajectories collected from a closed-loop system. Our approach does not require an analytic expression of the closed-loop dynamics, thus enabling safety verification of systems with complex models and controllers. Our framework consists of an offline stage that initializes a safety assessment function by simulating a nominal model and an online stage that adapts the function to address the sim-to-real gap. The performance of the proposed approach for safety verification is demonstrated using a quadruped balancing task and a humanoid reaching task. The results demonstrate that our framework accurately predicts the systems' safety both at the planning phase to generate robust trajectories and at execution phase to detect unexpected external disturbances., Comment: 8 pages, 8 figures, submitted to RA-L with IROS option

We introduce a family of highly symmetric bipartite quantum states in arbitrary dimensions. It consists of all states that are invariant under local phase rotations and local cyclic permutations of the basis. We solve the separability problem for a subspace of these states and show that a sizable part of the family is bound entangled. We also calculate some of the Schmidt numbers for the family in $d = 3$, thereby characterizing the dimensionality of entanglement. Our results allow us to estimate entanglement properties of arbitrary states, as general states can be symmetrized to the considered family by local operations., Comment: 15 pages, 5 figures. Comments are welcome!

Shared autonomy provides a framework where a human and an automated system, such as a robot, jointly control the system's behavior, enabling an effective solution for various applications, including human-robot interaction. However, a challenging problem in shared autonomy is safety because the human input may be unknown and unpredictable, which affects the robot's safety constraints. If the human input is a force applied through physical contact with the robot, it also alters the robot's behavior to maintain safety. We address the safety issue of shared autonomy in real-time applications by proposing a two-layer control framework. In the first layer, we use the history of human input measurements to infer what the human wants the robot to do and define the robot's safety constraints according to that inference. In the second layer, we formulate a rapidly-exploring random tree of barrier pairs, with each barrier pair composed of a barrier function and a controller. Using the controllers in these barrier pairs, the robot is able to maintain its safe operation under the intervention from the human input. This proposed control framework allows the robot to assist the human while preventing them from encountering safety issues. We demonstrate the proposed control framework on a simulation of a two-linkage manipulator robot., Comment: Accepted in Proceedings of the 60th IEEE Conference on Decision and Control

We investigate the relative volume of parent Hamiltonians having a target ground state up to some fixed error $\epsilon$, a quantity which sets a benchmark on the performance of quantum simulators. For vanishing error, this relative volume is of measure zero, whereas for a generic $\epsilon$ we show that it increases with the dimension of the Hilbert space. We also address the volume of parent Hamiltonians when they are restricted to be local. For translationally invariant Hamiltonians, we provide an upper bound to their relative volume. Finally, we estimate numerically the relative volume of parent Hamiltonians when the target state is the ground state of the Ising chain in a transverse field., Comment: published version

The optical response of nickel is studied in a wide range of laser fluence, below and above the ablation threshold, by selfreflectivity measurements of ultrashort 800nm single laser pulses. At the ablation threshold, the reflectivity remains unchanged with respect to its unperturbed value irrespective of the pulse duration, from 15 to 100 fs, consistently with the steadiness of the laser-induced ablation threshold fluence Fth for all pulse durations tested. Until the ablation threshold ($F\le F_{th}$) and whatever the pulse duration, the disturbances caused to the initial structure of the electron gas distribution by the laser energy deposition are limited, having no significant impact on the transient optical response of nickel and on its ablation threshold. At higher laser fluences ($F> F_{th}$), the reflectivity becomes rapidly dominated by the contribution to the optical response of the fast-thermalized free electrons (4s-band) with energy largely above the Fermi energy level. In these conditions, the reflectivity decreases for all pulse durations enhancing laser energy coupling and larger optical absorption at the surface of nickel. The optical response of nickel under ultrashort (15-100 fs) irradiation is thus fully elucidated on a wide range of fluence (0.3 $F_{th}$ - 30 $F_{th}$) and for pulse duration down to few-optical-cycle pulse duration. As a key parameter for benchmarking laser-matter interaction in poorly known conditions yet, the evolution of the effective electron collision rate is determined as a function of fluence and pulse duration in very good consistency with experiments.

This paper proposes an online path planning and motion generation algorithm for heterogeneous robot teams performing target search in a real-world environment. Path selection for each robot is optimized using an information-theoretic formulation and is computed sequentially for each agent. First, we generate candidate trajectories sampled from both global waypoints derived from vertical cell decomposition and local frontier points. From this set, we choose the path with maximum information gain. We demonstrate that the hierarchical sequential decision-making structure provided by the algorithm is scalable to multiple agents in a simulation setup. We also validate our framework in a real-world apartment setting using a two robot team comprised of the Unitree A1 quadruped and the Toyota HSR mobile manipulator searching for a person. The agents leverage an efficient leader-follower communication structure where only critical information is shared., Comment: 6 pages, 6 figures

We consider online strategies for discriminating between symmetric pure states with zero error when $n$ copies of the states are provided. Optimized online strategies involve local, possibly adaptive measurements on each copy and are optimal at each step, which makes them robust in front of particle losses or an abrupt termination of the discrimination process. We first review previous results on binary minimum and zero error discrimination with local measurements that achieve the maximum success probability set by optimizing over global measurements, highlighting their online features. We then extend these results to the case of zero error identification of three symmetric states with constant overlap. We provide optimal online schemes that attain global performance for any $n$ if the state overlaps are positive, and for odd $n$ if overlaps have a negative value. For arbitrary complex overlaps, we show compelling evidence that online schemes fail to reach optimal global performance. The online schemes that we describe only require to store the last outcome obtained in a classical memory, and adaptiveness of the measurements reduce to at most two changes, regardless of the value of $n$., Comment: 12 pages, 1 figure

We introduce sequential analysis in quantum information processing, by focusing on the fundamental task of quantum hypothesis testing. In particular our goal is to discriminate between two arbitrary quantum states with a prescribed error threshold, $\epsilon$, when copies of the states can be required on demand. We obtain ultimate lower bounds on the average number of copies needed to accomplish the task. We give a block-sampling strategy that allows to achieve the lower bound for some classes of states. The bound is optimal in both the symmetric as well as the asymmetric setting in the sense that it requires the least mean number of copies out of all other procedures, including the ones that fix the number of copies ahead of time. For qubit states we derive explicit expressions for the minimum average number of copies and show that a sequential strategy based on fixed local measurements outperforms the best collective measurement on a predetermined number of copies. Whereas for general states the number of copies increases as $\log 1/\epsilon$, for pure states sequential strategies require a finite average number of samples even in the case of perfect discrimination, i.e., $\epsilon=0$., Comment: 17 pages, 8 figures

Model-based reinforcement learning (MBRL) algorithms can attain significant sample efficiency but require an appropriate network structure to represent system dynamics. Current approaches include white-box modeling using analytic parameterizations and black-box modeling using deep neural networks. However, both can suffer from a bias-variance trade-off in the learning process, and neither provides a structured method for injecting domain knowledge into the network. As an alternative, gray-box modeling leverages prior knowledge in neural network training but only for simple systems. In this paper, we devise a nested mixture of experts (NMOE) for representing and learning hybrid dynamical systems. An NMOE combines both white-box and black-box models while optimizing bias-variance trade-off. Moreover, an NMOE provides a structured method for incorporating various types of prior knowledge by training the associative experts cooperatively or competitively. The prior knowledge includes information on robots' physical contacts with the environments as well as their kinematic and dynamic properties. In this paper, we demonstrate how to incorporate prior knowledge into our NMOE in various continuous control domains, including hybrid dynamical systems. We also show the effectiveness of our method in terms of data-efficiency, generalization to unseen data, and bias-variance trade-off. Finally, we evaluate our NMOE using an MBRL setup, where the model is integrated with a model-based controller and trained online., Comment: Accepted to 2021 L4DC