arXiv AI August 19, 2026 By Amir Arsalan Nematollahi, Shayan Ahmadi, Mehdi Tale Masouleh, Ahmad Kalhor

Iterative Grasp Pose Refinement: A Deep Reinforcement Learning Approach for 2D Vision

The paper presents a reinforcement learning framework that refines robotic grasp poses using a Deep Q-Network and keypoint-based object representations. Starting from initial grasp candidates generated by a geometric algorithm on 2D overhead images, the method iteratively improves grasps, converting previously failed attempts into successful ones. Experiments on 300 Dex‑Net objects with a UR5 arm achieved a 100% success rate on items that were ungraspable by geometry alone, and the approach transferred to a Delta robot in real‑world tests.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 16

Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videos

arXiv:2602. 13197v2 Announce Type: replace-cross Abstract: The ability to learn manipulation skills by watching videos of humans has the potential to unlock a new source of highly scalable data for robot learning.

By Albert J. Zhai, Kuo-Hao Zeng, Jiasen Lu, Ali Farhadi, Shenlong Wang, Wei-Chiu Ma

robotics

arXiv AI

Aug 21

GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation

arXiv:2608. 19759v1 Announce Type: cross Abstract: Multifingered grasping is a crucial robotic skill, but current deep-learning grasp planners often struggle to generalize to new objects because they are trained on limited, object-specific datasets.

By Julien Merand, Boris Meden, Mathieu Grossard, Liming Chen

robotics benchmarks

arXiv Machine Learning

1d ago

Continual Learning for 6-DoF Grasp Synthesis via Experience and Demonstrations

The paper introduces a continual‑learning framework for single‑view 6‑DoF grasp synthesis with a parallel‑jaw gripper in cluttered scenes. Instead of fine‑tuning a large parametric model, the method updates grasp scores via memory in a learned embedding space and optionally incorporates user demonstrations to generate new candidate grasps. Experiments in simulation and real‑world trials (over 1500 grasps) show that the approach matches baseline performance before adaptation, improves online on unseen objects, and achieves over 90% success on challenging categories after just 50 online attempts.

By Giulio Schiavi, Andrei Cramariuc, Michael Pantic, Roland Siegwart

rag robotics fine-tuning

arXiv AI

Jul 2

Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration

arXiv:2607. 00033v1 Announce Type: cross Abstract: Dexterous robot manipulation can benefit from the abundance of human demonstrations, but transferring such demonstrations to robot policies remains challenging.

By Xinghao Zhu, Zixi Liu, Shalin Jain, Chenran Li, Milad Noori, Huihua Zhao, John Welsh, Michael Andres Lin, Wei Liu, Tingwu Wang, Xingye Da, Zhengyi Luo, Vishal Kulkarni, Naema Bhatti, Yuke Zhu, Linxi Fan, Bowen Wen, Danfei Xu, Soha Pouya, Yan Chang

reinforcement-learning robotics benchmarks

arXiv Machine Learning

Jun 10

Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations

arXiv:2606. 10614v1 Announce Type: cross Abstract: Robotic foundation models pre-trained on human demonstration videos have shown promise, but a significant embodiment gap remains when the resulting policies are deployed on real robots.

By Beomjun Kim, Seong Hyeon Park, Seunghoon Sim, Seungjun Moon, Sanghyeok Lee, Jinwoo Shin

llms agents robotics fine-tuning benchmarks

arXiv AI

Jun 18

Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation

arXiv:2606. 18594v1 Announce Type: cross Abstract: In real-world reinforcement learning (RL), the choice of action space can play a key role in shaping motion smoothness, safety, and overall task performance.

By Seyed Alireza Azimi, Homayoon Farrahi, Abhishek Naik, Colin Bellinger, A. Rupam Mahmood

reinforcement-learning robotics benchmarks safety

One email a morning, machine-written

Related stories

Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videos

GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation

Continual Learning for 6-DoF Grasp Synthesis via Experience and Demonstrations

Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration

Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations

Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation