6 accepted papers
In this paper, we present a low-cost, easy-to-implement sim-to-real framework for biped locomotion that narrows the reality gap using only simulation data, without motion-capture or additional real-world measurements. First, a walking policy for the BRUCE robot is trained in Isaac Gym via reinforcem…
In this paper, we present a low-cost, easy-to-implement sim-to-real framework for biped locomotion that narrows the reality gap using only simulation data, without motion-capture or additional real-world measurements. First, a walking policy for the BRUCE robot is trained in Isaac Gym via reinforcem
This paper introduces a novel climbing robot for tube-sheet inspection (CRTI) that uses inner wall grippers (IWGs) to grasp tubes, enabling it to hang and crawl beneath the tube-sheet plane. The robot is designed primarily for inspecting steam generators in nuclear power plants. The CRTI based on a
This study proposes a pose and path planning method based on direction fields, addressing challenges in industrial robot surface machining. These challenges include limited machining accuracy and difficult path planning arising from the robot's low stiffness and high nonlinearity between joint and o
Inimitation learning, it is often assumed the demonstration data are optimal, even though they are imperfect in practice. The imperfect demonstrations result from expert errors, large-scale demonstration data, and the non-convexity of the solution space of the task. In this letter, we propose a new
Soft grippers exhibit impressive grasping performance with great simplicity, compliance, adaptability, and robustness. However, it is a great challenge for them to achieve high-load carrying capacity. Here, we present a soft fabric gripper to achieve high-load carrying capacity. The gripper features