5 papers · 1 filter
Cross-Embodiment Robotic Manipulation Synthesis via Guided Demonstrations through CycleVAE and Human Behavior Transformer
Apan Dastider, Hao Fang, Mingjie Lin
Cross-embodiment robotic manipulation synthesis for complicated tasks is challenging, partially due to the scarcity of paired cross-embodiment datasets and the impediment of design…
APEX: Ambidextrous Dual-Arm Robotic Manipulation Using Collision-Free Generative Diffusion Models
Apan Dastider, Hao Fang, Mingjie Lin
Dexterous manipulation, particularly adept coordinating and grasping, constitutes a fundamental and indispensable capability for robots, facilitating the emulation of human-like be…
Non-Parametric Stochastic Policy Gradient with Strategic Retreat for Non-Stationary Environment
Apan Dastider, Mingjie Lin
In modern robotics, effectively computing optimal control policies under dynamically varying environments poses substantial challenges to the off-the-shelf parametric policy gradie…
Survivable Robotic Control through Guided Bayesian Policy Search with Deep Reinforcement Learning
Sayyed Jaffar Ali Raza, Apan Dastider, Mingjie Lin
Many robot manipulation skills can be represented with deterministic characteristics and there exist efficient techniques for learning parameterized motor plans for those skills. H…
Survivable Hyper-Redundant Robotic Arm with Bayesian Policy Morphing
Sayyed Jaffar Ali Raza, Apan Dastider, Mingjie Lin
In this paper we present a Bayesian reinforcement learning framework that allows robotic manipulators to adaptively recover from random mechanical failures autonomously, hence bein…