no code implementations • 27 Sep 2022 • Apan Dastider, Hao Fang, Mingjie Lin
Real-time interception of fast-moving objects by robotic arms in dynamic environments poses a formidable challenge due to the need for rapid reaction times, often within milliseconds, amidst dynamic obstacles.
no code implementations • 24 Mar 2022 • 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 gradient methods, such as the Deep Deterministic Policy Gradient (DDPG) and Twin Delayed Deep Deterministic policy gradient (TD3).
no code implementations • 24 Mar 2022 • Apan Dastider, Mingjie Lin
Our methodology provides a robust and effective solution for safe human-robot collaboration in non-stationary environments.
no code implementations • 20 Oct 2020 • 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 being survivable.