cs.RO · 2026-08-24 · No. 94

Robotics, 2026-08-24.

4 new papers in cs.RO. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

4 entries
  1. 01

    Beyond Imitation: Self-Improving Robot Policies via Off-Policy Q-Planning

    Varun Giridhar, Anant Khandelwal, Jeremy A. Collins, Ignat Georgiev, Animesh Garg

    cs.RO · cs.LG

    Behaviour Cloning (BC) has driven remarkable progress in robot manipulation, yet it is fundamentally limited by its inability to self-improve: a policy that fails cannot learn from that failure without additional human demonstrations. Reinforcement Learning fine-tuning offers a path to self-improvement but has proven difficult to scale to the multi-billion-parameter models underpinning modern robot policies. We propose Q-Planning, which...

    arxiv.org/abs/2608.21204 · PDF

  2. 02

    SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control

    Ruihua Han, Rui Gao, Zhe Liu, Xinyi Wang, Chang Chen, Shuai Wang, Qi Hao, Jia Pan, Hengshuang Zhao

    cs.RO · cs.AI

    Safe and efficient shape-aware navigation in heterogeneous crowds and robot fleets remains challenging. Traditional approaches often assume homogeneous robots, sparse workspaces, simplified geometry, offline computation, or handcrafted parameters to make the problem tractable, which limits their deployment in dense crowd scenarios. Toward this end, we propose Shape-Aware Reinforcement Learned Model Predictive Control (SRL-MPC), a method for...

    arxiv.org/abs/2608.21175 · PDF

  3. 03

    Neural-Primitive: An Efficient End-to-end Local Planner with Primitive-based Imitation Learning for Autonomous Flight

    Zhitao Liu, Guangtong Xu, Zihan Wang, Jialiang Hou, Chao Xu, Fei Gao

    cs.RO · cs.AI

    Autonomous flight in unknown cluttered environments is hindered by the computation-quality-memory trilemma of onboard trajectory generation. In this paper, we propose an efficient end-to-end local planner via imitation learning. A lightweight offline-primitive-based dataset collection framework is designed to produce safe and high-quality trajectory primitives in non-convex environments. A compact neural network directly maps sensory inputs...

    arxiv.org/abs/2608.20948 · PDF

  4. 04

    Rethinking Demonstration Unlearning in Imitation Learning for Robotics

    Jiazhuo Li, Yu Zhang, Yiming Fei, Kangkang Dong, Xiaojun Zhu, Houde Liu, Jinze Tao

    cs.RO · cs.LG

    Imitation learning for robotics depends on human demonstrations, some of which people may later ask to remove. Retraining without them is the natural reference, but its cost grows with policy and dataset scale, motivating cheaper operators that edit a trained policy. Metrics inherited from machine unlearning, such as forgetting loss or a single membership attack, do not establish what an edit removed from a policy acting in closed loop. We...

    arxiv.org/abs/2608.20784 · PDF

This edition is part of The Daily Abstract — cs.RO archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.