检索结果-内蒙古大学图书馆

Leveraging Pretrained Latent Representations for Few-Shot Imitation learning on an Anthropomorphic Robotic Hand 23

学校读者我要写书评

暂无评论

Leveraging Pretrained Latent Representations for Few-Shot Im...

23rd IEEE-RAS International Conference on Humanoid Robots, Humanoids 2024

作者： Liconti, Davide Toshimitsu, Yasunori Katzschmann, Robert Eth Zurich Soft Robotics Lab Iris D-MAVT Switzerland Max Plank Eth Center for Learning Systems Germany

ISBN: (纸本)9798350373578

In the context of imitation learning applied to anthropomorphic robotic hands, the high complexity of the systems makes learning complex manipulation tasks challenging. However, the numerous datasets depicting human hands in various different tasks could provide us with better knowledge regarding human hand motion. We propose a method to leverage multiple large-scale task-agnostic datasets to obtain latent representations that effectively encode motion subtrajectories that we included in a transformer-based behavior cloning method. Our results demonstrate that employing latent representations yields enhanced performance compared to conventional behavior cloning methods, particularly regarding resilience to errors and noise in perception and proprioception. Furthermore, the proposed approach solely relies on human demonstrations, eliminating the need for teleoperation and, therefore, accelerating the data acquisition process. Accurate inverse kinematics for fingertip retargeting ensures precise transfer from human hand data to the robot, facilitating effective learning and deployment of manipulation policies. Finally, the trained policies have been successfully transferred to a real-world 23Dof robotic system. © 2024 IEEE.

关键词： Inverse kinematics

learning More With Less: Sample Efficient Dynamics learning and Model-Based RL for Loco-Manipulation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hoffman, Benjamin Cheng, Jin Li, Chenhao Coros, Stelian ETH Zurich Switzerland Computational Robotics Lab The Learning and Adaptive Systems Group Robotic Systems Lab ETH Zurich Switzerland

Combining the agility of legged locomotion with the capabilities of manipulation, loco-manipulation platforms have the potential to perform complex tasks in real-world applications. To this end, state-of-the-art quadrupeds with attached manipulators, such as the Boston Dynamics Spot, have emerged to provide a capable and robust platform. However, both the complexity of loco-manipulation control, as well as the black-box nature of commercial platforms pose challenges for developing accurate dynamics models and control policies. We address these challenges by developing a hand-crafted kinematic model for a quadruped-with-arm platform and, together with recent advances in Bayesian Neural Network (BNN)–based dynamics learning using physical priors, efficiently learn an accurate dynamics model from data. We then derive control policies for loco-manipulation via model-based reinforcement learning (RL). We demonstrate the effectiveness of this approach on hardware using the Boston Dynamics Spot with a manipulator, accurately performing dynamic end-effector trajectory tracking even in low data regimes. Copyright © 2025, The Authors. All rights reserved.

关键词： Manipulators

Diffusion Predictive Control with Constraints

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Römer, Ralf von Rohr, Alexander Schoellig, Angela P. Learning Systems and Robotics Lab Technical University of Munich Munich80333 Germany Germany

Diffusion models have recently gained popularity for policy learning in robotics due to their ability to capture high-dimensional and multimodal distributions. However, diffusion policies are inherently stochastic and typically trained offline, limiting their ability to handle unseen and dynamic conditions where novel constraints not represented in the training data must be satisfied. To overcome this limitation, we propose diffusion predictive control with constraints (DPCC), an algorithm for diffusion-based control with explicit state and action constraints that can deviate from those in the training data. DPCC uses constraint tightening and incorporates model-based projections into the denoising process of a trained trajectory diffusion model. This allows us to generate constraint-satisfying, dynamically feasible, and goal-reaching trajectories for predictive control. We show through simulations of a robot manipulator that DPCC outperforms existing methods in satisfying novel test-time constraints while maintaining performance on the learned control task. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

Sensor Query Schedule and Sensor Noise Covariances for Accuracy-constrained Trajectory Estimation

学校读者我要写书评

暂无评论

IEEE robotics and Automation Letters 2025年第7期10卷 6983-6990页

作者： Goudar, Abhishek Schoellig, Angela P. Technical University of Munich Learning Systems and Robotics Lab Germany University of Toronto Institute for Aerospace Studies Canada Vector Institute for Artificial Intelligence Canada

Trajectory estimation involves determining the trajectory of a mobile robot by combining prior knowledge about its dynamic model with noisy observations of its state obtained using sensors. The accuracy of such a procedure is dictated by the system model fidelity and the sensor parameters, such as the accuracy of the sensor (as represented by its noise covariance) and the rate at which it can generate observations, referred to as the sensor query schedule. Intuitively, high-rate measurements from accurate sensors lead to accurate trajectory estimation. However, cost and resource constraints limit the sensor accuracy and its measurement rate. Our work's novel contribution is the estimation of sensor schedules and sensor covariances necessary to achieve a specific estimation accuracy. Concretely, we focus on estimating: (i) the rate or schedule with which a sensor of known covariance must generate measurements to achieve specific estimation accuracy, and alternatively, (ii) the sensor covariance necessary to achieve specific estimation accuracy for a given sensor update rate. We formulate the problem of estimating these sensor parameters as semidefinite programs, which can be solved by off-the-shelf solvers. We validate our approach in simulation and real experiments by showing that the sensor schedules and the sensor covariances calculated using our proposed method achieve the desired trajectory estimation accuracy. Our method also identifies scenarios where certain estimation accuracy is unachievable with the given system and sensor characteristics. © 2016 IEEE.

关键词： Robot sensing systems Estimation Accuracy Schedules Trajectory Noise Time measurement Estimation error Covariance matrices Uncertainty

Automated Planning Domain Inference for Task and Motion Planning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Huang, Jinbang Tao, Allen Marco, Rozilyn Bogdanovic, Miroslav Kelly, Jonathan Shkurti, Florian Space and Terrestrial Autonomous Systems Lab Canada Robot Vision and Learning Lab University of Toronto Robotics Institute Canada

Task and motion planning (TAMP) frameworks address long and complex planning problems by integrating high-level task planners with low-level motion planners. However, existing TAMP methods rely heavily on the manual design of planning domains that specify the preconditions and postconditions of all high-level actions. This paper proposes a method to automate planning domain inference from a handful of test-time trajectory demonstrations, reducing the reliance on human design. Our approach incorporates a deep learning-based estimator that predicts the appropriate components of a domain for a new task and a search algorithm that refines this prediction, reducing the size and ensuring the utility of the inferred domain. Our method is able to generate new domains from minimal demonstrations at test time, enabling robots to handle complex tasks more efficiently. We demonstrate that our approach outperforms behavior cloning baselines, which directly imitate planner behavior, in terms of planning performance and generalization across a variety of tasks. Additionally, our method reduces computational costs and data amount requirements at test time for inferring new planning domains. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion planning

Is Data All That Matters? the Role of Control Frequency for learning-Based Sampled-Data Control of Uncertain systems

学校读者我要写书评

暂无评论

Is Data All That Matters? the Role of Control Frequency for ...

American Control Conference (ACC)

作者： Ralf Römer Lukas Brunke Siqi Zhou Angela P. Schoellig Learning Systems and Robotics Lab (***) School of Computation Information and Technology and the Munich Institute for Robotics and Machine Intelligence (MIRMI) Technical University of Munich Germany

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

learning models or control policies from data has become a powerful tool to improve the performance of uncertain systems. While a strong focus has been placed on increasing the amount and quality of data to improve performance, data can never fully eliminate uncertainty, making feedback necessary to ensure stability and performance. We show that the control frequency at which the input is recalculated is a crucial design parameter, yet it has hardly been considered before. We address this gap by combining probabilistic model learning and sampled-data control. We use Gaussian processes (GPs) to learn a continuous-time model and compute a corresponding discrete-time controller. The result is an uncertain sampled-data control system, for which we derive robust stability conditions. We formulate semidefinite programs to compute the minimum control frequency required for stability and to optimize performance. As a result, our approach enables us to study the effect of both control frequency and data on stability and closed-loop performance. We show in numerical simulations of a quadrotor that performance can be improved by increasing either the amount of data or the control frequency, and that we can trade off one for the other. For example, by increasing the control frequency by 33%, we can reduce the number of data points by half while still achieving similar performance.

关键词： Uncertain systems Uncertainty Robust stability Computational modeling Control systems Stability analysis Data models

Safety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement learning Agents

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bejarano, Federico Pizarro Brunke, Lukas Schoellig, Angela P. The Learning Systems and Robotics Lab University of Toronto Canada The University of Toronto Robotics Institute The Vector Institute for Artificial Intelligence Toronto Canada Germany

Reinforcement learning (RL) controllers are flexible and performant but rarely guarantee safety. Safety filters impart hard safety guarantees to RL controllers while maintaining flexibility. However, safety filters can cause undesired behaviours due to the separation between the controller and the safety filter, often degrading performance and robustness. In this paper, we analyze several modifications to incorporating the safety filter in training RL controllers rather than solely applying it during evaluation. The modifications allow the RL controller to learn to account for the safety filter, improving performance. This paper presents a comprehensive analysis of training RL with safety filters, featuring simulated and real-world experiments with a Crazyflie 2.0 drone. We examine how various training modifications and hyperparameters impact performance, sample efficiency, safety, and chattering. Our findings serve as a guide for practitioners and researchers focused on safety filters and safe RL. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Practical Considerations for Discrete-Time Implementations of Continuous-Time Control Barrier Function-Based Safety Filters

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Brunke, Lukas Zhou, Siqi Che, Mingxuan Schoellig, Angela P. The Learning Systems and Robotics Lab The Technical University of Munich Germany The University of Toronto Canada The University of Toronto Robotics Institute The Vector Institute for Artificial Intelligence Canada

Safety filters based on control barrier functions (CBFs) have become a popular method to guarantee safety for uncertified control policies, e.g., as resulting from reinforcement learning. Here, safety is defined as staying in a pre-defined set, the safe set, that adheres to the system's state constraints, e.g., as given by lane boundaries for a self-driving vehicle. In this paper, we examine one commonly overlooked problem that arises in practical implementations of continuous-time CBF-based safety filters. In particular, we look at the issues caused by discrete-time implementations of the continuous-time CBF-based safety filter, especially for cases where the magnitude of the Lie derivative of the CBF with respect to the control input is zero or close to zero. When overlooked, this filter can result in undesirable chattering effects or constraint violations. In this work, we propose three mitigation strategies that allow us to use a continuous-time safety filter in a discrete-time implementation with a local relative degree. Using these strategies in augmented CBF-based safety filters, we achieve safety for all states in the safe set by either using an additional penalty term in the safety filtering objective or modifying the CBF such that those undesired states are not encountered during closed-loop operation. We demonstrate the presented issue and validate our three proposed mitigation strategies in simulation and on a real-world quadrotor. Copyright © 2024, The Authors. All rights reserved.

关键词： Continuous time systems

Leveraging Pretrained Latent Representations for Few-Shot Imitation learning on an Anthropomorphic Robotic Hand

学校读者我要写书评

暂无评论

Leveraging Pretrained Latent Representations for Few-Shot Im...

IEEE-RAS International Conference on Humanoid Robots

作者： Davide Liconti Yasunori Toshimitsu Robert Katzschmann D-MAVT Soft Robotics Lab IRIS ETH Zurich Switzerland Max Plank ETH Center for Learning Systems

ISBN: (数字)9798350373578

ISBN: (纸本)9798350373585

关键词： Imitation learning Noise Data acquisition Cloning Humanoid robots Grasping Data collection Transformers Trajectory Resilience