arXiv subjects

Luis Sentis

Publications and source records attributed to Luis Sentis.

At least 55 records · Page 3Linked to original sources

arXiv2021

Active Object Tracking using Context Estimation: Handling Occlusions and Detecting Missing Targets

When performing visual servoing or object tracking tasks, active sensor planning is essential to keep targets in sight or to relocate them when missing. In particular, when dealing with a known target missing from the sensor's field of view, we propose using prior knowledge related to contextual information to estimate its possible location. To this end, this study proposes a Dynamic Bayesian Network that uses contextual information to effectively search for targets. Monte Carlo particle filtering is employed to approximate the posterior probability of the target's state, from which uncertainty is defined. We define the robot's utility function via information-theoretic formalism as seeking the optimal action which reduces uncertainty of a task, prompting robot agents to investigate the location where the target most likely might exist. Using a context state model, we design the agent's high-level decision framework using a Partially-Observable Markov Decision Process. Based on the estimated belief state of the context via sequential observations, the robot's navigation actions are determined to conduct exploratory and detection tasks. By using this multi-modal context model, our agent can effectively handle basic dynamic events, such as obstruction of targets or their absence from the field of view. We implement and demonstrate these capabilities on a mobile robot in real-time.

cs.RO↗

arXiv2021

A Barrier Pair Method for Safe Human-Robot Shared Autonomy

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.

cs.RO↗

arXiv2021

Information-Theoretic Based Target Search with Multiple Agents

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.

cs.RO↗

arXiv2021

Robust and Adaptive Door Operation with a Mobile Robot

The ability to deal with articulated objects is very important for robots assisting humans. In this work, a framework to robustly and adaptively operate common doors, using an autonomous mobile manipulator, is proposed. To push forward the state-of-the-art in robustness and speed performance, we devise a novel algorithm that fuses a convolutional neural network with efficient point cloud processing. This advancement enables real-time grasping pose estimation for multiple handles from RGB-D images, providing a speed up improvement for assistive human-centered applications. In addition, we propose a versatile Bayesian framework that endows the robot with the ability to infer the door kinematic model from observations of its motion and learn from previous experiences or human demonstrations. Combining these algorithms with a Task Space Region motion planner, we achieve an efficient door operation regardless of the kinematic model. We validate our framework with real-world experiments using the Toyota Human Support Robot.

cs.RO↗

arXiv2021

Nested Mixture of Experts: Cooperative and Competitive Learning of Hybrid Dynamical System

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.

cs.LG↗

arXiv2021

Task-Adaptive Robot Learning from Demonstration with Gaussian Process Models under Replication

Learning from Demonstration (LfD) is a paradigm that allows robots to learn complex manipulation tasks that can not be easily scripted, but can be demonstrated by a human teacher. One of the challenges of LfD is to enable robots to acquire skills that can be adapted to different scenarios. In this paper, we propose to achieve this by exploiting the variations in the demonstrations to retrieve an adaptive and robust policy, using Gaussian Process (GP) models. Adaptability is enhanced by incorporating task parameters into the model, which encode different specifications within the same task. With our formulation, these parameters can be either real, integer, or categorical. Furthermore, we propose a GP design that exploits the structure of replications, i.e., repeated demonstrations with identical conditions within data. Our method significantly reduces the computational cost of model fitting in complex tasks, where replications are essential to obtain a robust model. We illustrate our approach through several experiments on a handwritten letter demonstration dataset.

cs.RO↗

arXiv2020

A Complex Stiffness Human Impedance Model with Customizable Exoskeleton Control

The natural impedance, or dynamic relationship between force and motion, of a human operator can determine the stability of exoskeletons that use interaction-torque feedback to amplify human strength. While human impedance is typically modelled as a linear system, our experiments on a single-joint exoskeleton testbed involving 10 human subjects show evidence of nonlinear behavior: a low-frequency asymptotic phase for the dynamic stiffness of the human that is different than the expected zero, and an unexpectedly consistent damping ratio as the stiffness and inertia vary. To explain these observations, this paper considers a new frequency-domain model of the human joint dynamics featuring complex value stiffness comprising a real stiffness term and a hysteretic damping term. Using a statistical F-test we show that the hysteretic damping term is not only significant but is even more significant than the linear damping term. Further analysis reveals a linear trend linking hysteretic damping and the real part of the stiffness, which allows us to simplify the complex stiffness model down to a 1-parameter system. Then, we introduce and demonstrate a customizable fractional-order controller that exploits this hysteretic damping behavior to improve strength amplification bandwidth while maintaining stability, and explore a tuning approach which ensures that this stability property is robust to muscle co-contraction for each individual.

cs.RO↗

arXiv2020

MPC-Based Hierarchical Task Space Control of Underactuated and Constrained Robots for Execution of Multiple Tasks

This paper proposes an MPC-based controller to efficiently execute multiple hierarchical tasks for underactuated and constrained robotic systems. Existing task-space controllers or whole-body controllers solve instantaneous optimization problems given task trajectories and the robot plant dynamics. However, the task-space control method we propose here relies on the prediction of future state trajectories and the corresponding costs-to-go terms over a finite time-horizon for computing control commands. We employ acceleration energy error as the performance index for the optimization problem and extend it over the finite-time horizon of our MPC. Our approach employs quadratically constrained quadratic programming, which includes quadratic constraints to handle multiple hierarchical tasks, and is computationally more efficient than nonlinear MPC-based approaches that rely on nonlinear programming. We validate our approach using numerical simulations of a new type of robot manipulator system, which contains underactuated and constrained mechanical structures.

cs.RO↗

arXiv2020

BP-RRT: Barrier Pair Synthesis for Temporal Logic Motion Planning

For a nonlinear system (e.g. a robot) with its continuous state space trajectories constrained by a linear temporal logic specification, the synthesis of a low-level controller for mission execution often results in a non-convex optimization problem. We devise a new algorithm to solve this type of non-convex problems by formulating a rapidly-exploring random tree of barrier pairs, with each barrier pair composed of a quadratic barrier function and a full state feedback controller. The proposed method employs a rapid-exploring random tree to deal with the non-convex constraints and uses barrier pairs to fulfill the local convex constraints. As such, the method solves control problems fulfilling the required transitions of an automaton in order to satisfy given linear temporal logic constraints. At the same time it synthesizes locally optimal controllers in order to transition between the regions corresponding to the alphabet of the automaton. We demonstrate this new algorithm on a simulation of a two linkage manipulator robot.

cs.RO↗

arXiv2020

Robust Estimator-Based Safety Verification: A Vector Norm Approach

In this paper, we consider the problem of verifying safety constraint satisfaction for single-input single-output systems with uncertain transfer function coefficients. We propose a new type of barrier function based on a vector norm. This type of barrier function has a measurable upper bound without full state availability. An identifier-based estimator allows an exact bound for the uncertainty-based component of the barrier function estimate. Assuming that the system is safe initially allows an exponentially decreasing bound on the error due to the estimator transient. Barrier function and estimator synthesis is proposed as two convex sub-problems, exploiting linear matrix inequalities. The barrier function controller combination is then used to construct a safety backup controller. And we demonstrate the system in a simulation of a 1 degree-of-freedom human-exoskeleton interaction.

math.OC↗

arXiv2020

Adaptive Compliance Shaping with Human Impedance Estimation

Human impedance parameters play an integral role in the dynamics of strength amplification exoskeletons. Many methods are used to estimate the stiffness of human muscles, but few are used to improve the performance of strength amplification controllers for these devices. We propose a compliance shaping amplification controller incorporating an accurate online human stiffness estimation from surface electromyography (sEMG) sensors and stretch sensors connected to the forearm and upper arm of the human. These sensor values along with exoskeleton position and velocity are used to train a random forest regression model that accurately predicts a person's stiffness despite varying movement, relaxation, and muscle co-contraction. Our model's accuracy is verified using experimental test data and the model is implemented into the compliance shaping controller. Ultimately we show that the online estimation of stiffness can improve the bandwidth and amplification of the controller while remaining robustly stable.

eess.SY↗

arXiv2020

The Robot Economy: Here It Comes

Automation is not a new phenomenon, and questions about its effects have long followed its advances. More than a half-century ago, US President Lyndon B. Johnson established a national commission to examine the impact of technology on the economy, declaring that automation "can be the ally of our prosperity if we will just look ahead". In this paper, our premise is that we are at a technological inflection point in which robots are developing the capacity to greatly increase their cognitive and physical capabilities, and thus raising questions on labor dynamics. With increasing levels of autonomy and human-robot interaction, intelligent robots could soon accomplish new human-like capabilities such as engaging into social activities. Therefore, an increase in automation and autonomy brings the question of robots directly participating in some economic activities as autonomous agents. In this paper, a technological framework describing a robot economy is outlined and the challenges it might represent in the current socio-economic scenario are pondered.

cs.RO↗

arXiv2020

Gaussian-Process-based Robot Learning from Demonstration

Endowed with higher levels of autonomy, robots are required to perform increasingly complex manipulation tasks. Learning from demonstration is arising as a promising paradigm for transferring skills to robots. It allows to implicitly learn task constraints from observing the motion executed by a human teacher, which can enable adaptive behavior. We present a novel Gaussian-Process-based learning from demonstration approach. This probabilistic representation allows to generalize over multiple demonstrations, and encode variability along the different phases of the task. In this paper, we address how Gaussian Processes can be used to effectively learn a policy from trajectories in task space. We also present a method to efficiently adapt the policy to fulfill new requirements, and to modulate the robot behavior as a function of task variability. This approach is illustrated through a real-world application using the TIAGo robot.

cs.RO↗

arXiv2020

Complex Stiffness Model of Physical Human-Robot Interaction: Implications for Control of Performance Augmentation Exoskeletons

Human joint dynamic stiffness plays an important role in the stability of performance augmentation exoskeletons. In this paper, we consider a new frequency domain model of the human joint dynamics which features a complex value stiffness. This complex stiffness consists of a real stiffness and a hysteretic damping. We use it to explain the dynamic behaviors of the human connected to the exoskeleton, in particular the observed non-zero low frequency phase shift and the near constant damping ratio of the resonant as stiffness and inertia vary. We validate this concept by experimenting with an elbow-joint exoskeleton testbed on a subject while modifying joint stiffness behavior, exoskeleton inertia, and strength augmentation gains. We compare three different models of elbow-joint dynamic stiffness: a model with real stiffness, viscous damping and inertia, a model with complex stiffness and inertia, and a model combining the previous two models. Our results show that the hysteretic damping term improves modeling accuracy, using a statistical F-test. Moreover this improvement is statistically more significant than using classical viscous damping term. In addition, we experimentally observe a linear relationship between the hysteretic damping and the real part of the stiffness which allows us to simplify the complex stiffness model as a 1-parameter system. Ultimately, we design a fractional order controller to demonstrate how human hysteretic damping behavior can be exploited to improve strength amplification performance while maintaining stability.

cs.RO↗

arXiv2020

Data-Efficient and Safe Learning for Humanoid Locomotion Aided by a Dynamic Balancing Model

In this letter, we formulate a novel Markov Decision Process (MDP) for safe and data-efficient learning for humanoid locomotion aided by a dynamic balancing model. In our previous studies of biped locomotion, we relied on a low-dimensional robot model, commonly used in high-level Walking Pattern Generators (WPGs). However, a low-level feedback controller cannot precisely track desired footstep locations due to the discrepancies between the full order model and the simplified model. In this study, we propose mitigating this problem by complementing a WPG with reinforcement learning. More specifically, we propose a structured footstep control method consisting of a WPG, a neural network, and a safety controller. The WPG provides an analytical method that promotes efficient learning while the neural network maximizes long-term rewards, and the safety controller encourages safe exploration based on step capturability and the use of control-barrier functions. Our contributions include the following (1) a structured learning control method for locomotion, (2) a data-efficient and safe learning process to improve walking using a physics-based model, and (3) the scalability of the procedure to various types of humanoid robots and walking.

cs.RO↗

arXiv2019

Safety Control Synthesis with Input Limits: a Hybrid Approach

We introduce a hybrid (discrete--continuous) safety controller which enforces strict state and input constraints on a system---but only acts when necessary, preserving transparent operation of the original system within some safe region of the state space. We define this space using a Min-Quadratic Barrier function, which we construct along the equilibrium manifold using the Lyapunov functions which result from linear matrix inequality controller synthesis for locally valid uncertain linearizations. We also introduce the concept of a barrier pair, which makes it easy to extend the approach to include trajectory-based augmentations to the safe region, in the style of LQR-Trees. We demonstrate our controller and barrier pair synthesis method in simulation-based examples.

math.OC↗

arXiv2019

Modeling and Loop Shaping of Single-Joint Amplification Exoskeleton with Contact Sensing and Series Elastic Actuation

In this paper we consider a class of exoskeletons designed to amplify the strength of humans through feedback of sensed human-robot interactions and actuator forces. We define an amplification error signal based on a reference amplification rate, and design a linear feedback compensator to attenuate this error. Since the human operator is an integral part of the system, we design the compensator to be robust to both a realistic variation in human impedance and a large variation in load impedance. We demonstrate our strategy on a one-degree of freedom amplification exoskeleton connected to a human arm, following a three dimensional matrix of experimentation: slow or fast human motion; light or extreme exoskeleton load; and soft or clenched human arm impedances. We demonstrate that a slightly aggressive controller results in a borderline stable system---but only for soft human musculoeskeletal behavior and a heavy load. This class of exoskeleton systems is interesting because it can both amplify a human's interaction forces --- so long as the human contacts the environment through the exoskeleton --- and attenuate the operator's perception of the exoskeleton's reflected dynamics at frequencies within the bandwidth of the control.

eess.SY↗

arXiv2019

Deploying the NASA Valkyrie Humanoid for IED Response: An Initial Approach and Evaluation Summary

As part of a feasibility study, this paper shows the NASA Valkyrie humanoid robot performing an end-to-end improvised explosive device (IED) response task. To demonstrate and evaluate robot capabilities, sub-tasks highlight different locomotion, manipulation, and perception requirements: traversing uneven terrain, passing through a narrow passageway, opening a car door, retrieving a suspected IED, and securing the IED in a total containment vessel (TCV). For each sub-task, a description of the technical approach and the hidden challenges that were overcome during development are presented. The discussion of results, which explicitly includes existing limitations, is aimed at motivating continued research and development to enable practical deployment of humanoid robots for IED response. For instance, the data shows that operator pauses contribute to 50\% of the total completion time, which implies that further work is needed on user interfaces for increasing task completion efficiency.

cs.RO↗