Hybrid Residual Reinforcement Learning for Contact-Rich Robotic Book Insertion

作者
Tianyuan Liu,Rutherford Agbeshi Patamia,Benjamin T. Champion,Akansel Cosgun,Richard Dazeley
出处
期刊:Cornell University - arXiv [Cornell University]
标识
DOI:10.48550/arxiv.2609.19962
摘要

Placing a grasped book into a tight shelf is a compact but difficult contact-rich control problem: millimetre-scale pose error can turn a geometrically valid approach into jamming, failed release, or incomplete seating. We study this final phase after grasp acquisition and global approach, and ask how control authority should be divided between known geometry and learned behaviour. Our method retains a nominal task-space controller for structured insertion and seating, while residual PPO supplies bounded local corrections and decides when to release. Only the brief open-retreat-reclose transition is scripted. For the final policy used on hardware, a deployment-matched simulation evaluation over 512 fixed conditions yields 98.50 percent mean success (0.23 percentage-point sample SD) across three independent training runs, compared with 37.89 percent for nominal control. On the physical xArm7, 60 trials over 30 matched conditions show the same qualitative advantage: residual control raises success from 26.7 percent to 63.3 percent, reduces failures from 22 to 11, and wins 13 of the 15 matched conditions in which the two controllers differ. Robustness tests show that performance remains above 87 percent under initialization perturbations up to 1.5x, while very tight clearances expose the geometric limit of local correction. These results support a hybrid design in which geometry preserves reliable task structure and learning is concentrated on the contact-sensitive behaviour that fixed rules handle poorly.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
yu完成签到,获得积分20
1秒前
1秒前
星辰大海的应助被WYL采纳,获得10
1秒前
2秒前
哈基米完成签到,获得积分10
2秒前
2秒前
3秒前
Hasson发布了新的文献求助10
3秒前
十一完成签到,获得积分10
3秒前
3秒前
drugster完成签到,获得积分10
3秒前
SciGPT的应助被heoouijee采纳,获得10
3秒前
112233完成签到,获得积分10
4秒前
桐桐的应助被香橙采纳,获得10
4秒前
所所的应助被流年采纳,获得10
4秒前
852的应助被务实的书芹采纳,获得10
4秒前
5秒前
CarryLJR发布了新的文献求助10
5秒前
研友_VZG7GZ的应助被flamez采纳,获得10
5秒前
天天快乐的应助被靓丽芙蓉采纳,获得10
5秒前
6秒前
6秒前
6秒前
zzzzz完成签到,获得积分10
6秒前
xgx984完成签到,获得积分10
6秒前
一杯芝士发布了新的文献求助10
6秒前
6秒前
Zero发布了新的文献求助10
6秒前
哈基米发布了新的文献求助10
6秒前
sss的应助被drizzle采纳,获得10
7秒前
专一的飞莲完成签到,获得积分10
7秒前
criz1完成签到,获得积分10
7秒前
7秒前
Vearseap完成签到,获得积分10
8秒前
一二三完成签到,获得积分10
8秒前
8秒前
冷静以山发布了新的文献求助10
8秒前
8秒前
8秒前
余香的应助被煌药师采纳,获得10
8秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
Resource Recovery Handbook 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8175707
求助须知:如何正确求助?哪些是违规求助? 9567353
关于积分的说明 21792214
捐赠科研通 7770334
什么是DOI,文献DOI怎么找? 3431908
关于科研通互助平台的介绍 2556260
邀请新用户注册赠送积分活动 2477417