Screw Geometry Meets Bandits: Incremental Acquisition of Demonstrations to Generate Manipulation Plans

2024-10-23 · Dibyendu Das, Aditya Patankar, Nilanjan Chakraborty, C. R. Ramakrishnan, I. V. Ramakrishnan

In this paper, we study the problem of methodically obtaining a sufficient set of kinesthetic demonstrations, one at a time, such that a robot can be confident of its ability to perform a complex manipulation task in a given region of its workspace. Although Learning from Demonstrations has been an active area of research, the problems of checking whether a set of demonstrations is sufficient, and systematically seeking additional demonstrations have remained open. We present a novel approach to address these open problems using (i) a screw geometric representation to generate manipulation plans from demonstrations, which makes the sufficiency of a set of demonstrations measurable; (ii) a sampling strategy based on PAC-learning from multi-armed bandit optimization to evaluate the robot's ability to generate manipulation plans in a subregion of its task space; and (iii) a heuristic to seek additional demonstration from areas of weakness. Thus, we present an approach for the robot to incrementally and actively ask for new demonstration examples until the robot can assess with high confidence that it can perform the task successfully. We present experimental results on two example manipulation tasks, namely, pouring and scooping, to illustrate our approach. A short video on the method: https://youtu.be/R-qICICdEos

📄 PDF Abstract BibTeX arXiv:2410.18275

Code (0)

등록된 구현이 없습니다.

Tasks

PAC learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Advancing 6-DoF Instrument Pose Estimation in Variable X-Ray Imaging Geometries

2024-05-19 · Christiaan G. A. Viviers, Lena Filatova, Maurice Termeer, Peter H. N. de With 외

Accurate 6-DoF pose estimation of surgical instruments during minimally invasive surgeries can substantially improve treatment strategies and eventual surgical outcome. Existing deep learning methods have achieved accura…

6D Pose Estimation GPU Pose Estimation

YOLOv5-6D: Advancing 6-DoF Instrument Pose Estimation in Variable X-Ray Imaging Geometries

2024-03-22 · IEEE Transactions on Image Processing 2024 3 · Christiaan G.A. Viviers, Lena Filatova, Maurice Termeer, Peter H.N. De With 외

6D Pose Estimation using RGB GPU Pose Estimation Real-Time Object Detection

SortScrews: A Dataset and Baseline for Real-time Screw Classification

2026-03-13 · Tianhao Fu, Bingxuan Yang, Juncheng Guo, Shrena Sribalan 외 arxiv

Automatic identification of screw types is important for industrial automation, robotics, and inventory management. However, publicly available datasets for screw classification are scarce, particularly for controlled si…

Transfer Learning

Manipulation Planning for Construction Activities with Repetitive Tasks

2026-05-13 · Wangyi Liu, Dasharadhan Mahalingam, Fanru Gao, Ci-Jyun Liang 외 arxiv

In this paper, we study the problem of manipulation skill acquisition for performing construction activities consisting of repetitive tasks (e.g., building a wall or installing ceiling tiles). Our approach involves setti…

DexTwist: Dexterous Hand Retargeting for Twist Motion via Mixed Reality-based Teleoperation

2026-05-12 · Dongmyoung Lee, Chengxi Li, Dongheui Lee arxiv

Dexterous teleoperation via Mixed Reality (MR)-based interfaces offers a scalable paradigm for transferring human manipulation skills to dexterous robot hands. However, conventional retargeting approaches that minimize k…