From imitation to refinement–residual rl for precise visual assembly

LL Ankile, A Simeonov, I Shenfeld… - … 2024 Workshop on …, 2024 - openreview.net
Recent advances in behavior cloning (BC), like action-chunking and diffusion, have led to
impressive progress. Still, imitation alone remains insufficient for tasks requiring reliable and …

Efficient skill acquisition for complex manipulation tasks in obstructed environments

J Yamada, J Collins, I Posner - arxiv preprint arxiv:2303.03365, 2023 - arxiv.org
Data efficiency in robotic skill acquisition is crucial for operating robots in varied small-batch
assembly settings. To operate in such environments, robots must have robust obstacle …

Extended residual learning with one-shot imitation learning for robotic assembly in semi-structured environment

C Wang, C Su, B Sun, G Chen, L **e - Frontiers in Neurorobotics, 2024 - frontiersin.org
Introduction Robotic assembly tasks require precise manipulation and coordination, often
necessitating advanced learning techniques to achieve efficient and effective performance …

From Imitation to Refinement--Residual RL for Precise Assembly

L Ankile, A Simeonov, I Shenfeld, M Torne… - arxiv preprint arxiv …, 2024 - arxiv.org
Recent advances in behavior cloning (BC), like action-chunking and diffusion, have led to
impressive progress. Still, imitation alone remains insufficient for tasks requiring reliable and …

Robot Learning Method for Human-like Arm Skills Based on the Hybrid Primitive Framework

J Li, H Han, J Hu, J Lin, P Li - Sensors, 2024 - mdpi.com
This paper addresses the issue of how to endow robots with motion skills, flexibility, and
adaptability similar to human arms. It innovatively proposes a hybrid-primitive-frame-based …

Utilizing human feedback for primitive optimization in wheelchair tennis

A Krishna, Z Zaidi, L Chen, R Paleja, E Seraj… - arxiv preprint arxiv …, 2022 - arxiv.org
Agile robotics presents a difficult challenge with robots moving at high speeds requiring
precise and low-latency sensing and control. Creating agile motion that accomplishes the …

Enhancing Robotic Adaptability: Integrating Unsupervised Trajectory Segmentation and Conditional ProMPs for Dynamic Learning Environments

T Gao - arxiv preprint arxiv:2404.19412, 2024 - arxiv.org
We propose a novel framework for enhancing robotic adaptability and learning efficiency,
which integrates unsupervised trajectory segmentation with adaptive probabilistic movement …

[PDF][PDF] Task and Motion Planning for Sequential Assembly-Towards Multi-View Multi-Marker Object Pose Estimation

P Hallmann, P Siebke, N Nonnengießer - ias.informatik.tu-darmstadt.de
In this work, we present a new approach to automate the process of construction using self-
interlocking building blocks specifically SL-Blocks. Utilizing this block type, complex …