Data-based Iterative Human-in-the-loop Robot-Learning for Output Tracking
Sign Up to like & getrecommendations! Published in 2017 at "IFAC-PapersOnLine"
DOI: 10.1016/j.ifacol.2017.08.2142
Abstract: Abstract This article develops a data-based approach for improved iterative robot-learning for output-tracking from novice human-in-the-loop demonstrations. While nominal human-response models can be used to improve iterative learning, the convergence can be slow due to… read more here.
Keywords: learning output; human loop; data based; output tracking ... See more keywords
Robot Learning of Mobile Manipulation With Reachability Behavior Priors
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2022.3188109
Abstract: Mobile Manipulation (MM) systems are ideal candidates for taking up the role of personal assistants in unstructured real-world environments. Among other challenges, Mobile Manipulation (MM) requires effective coordination of the robot’s embodiments for executing tasks… read more here.
Keywords: reachability; learning mobile; manipulation; policy ... See more keywords
Revisiting the Adversarial Robustness-Accuracy Tradeoff in Robot Learning
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2023.3240930
Abstract: Adversarial training (i.e., training on adversarially perturbed input data) is a well-studied method for making neural networks robust to potential adversarial attacks during inference. However, the improved robustness does not come for free but rather… read more here.
Keywords: robot learning; adversarial training; robustness accuracy; robot ... See more keywords
Robot Learning System Based on Adaptive Neural Control and Dynamic Movement Primitives
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Transactions on Neural Networks and Learning Systems"
DOI: 10.1109/tnnls.2018.2852711
Abstract: This paper proposes an enhanced robot skill learning system considering both motion generation and trajectory tracking. During robot learning demonstrations, dynamic movement primitives (DMPs) are used to model robotic motion. Each DMP consists of a… read more here.
Keywords: movement primitives; learning system; robot learning; dynamic movement ... See more keywords
Quantifying Demonstration Quality for Robot Learning and Generalization
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Robotics and Automation Letters"
DOI: 10.48550/arxiv.2203.13843
Abstract: Learning from Demonstration (LfD) seeks to democratize robotics by enabling non-expert end-users to teach robots. However, most LfD techniques assume users provide optimal demonstrations, which may not be accurate. Demonstration quality plays a crucial role… read more here.
Keywords: quality; robotics; robot learning; demonstration quality ... See more keywords