论文列表 2026-05-12

1

克服动力学盲：面向VLA模型的无需训练的步速与路径校正 Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models

Yanyan Zhang, Chaoda Song, Vikash Singh 等9人

2

TOPPO：用评论家平衡重新思考多任务强化学习的PPO TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing

Yuanpeng Li, Gefei Lin, Annie Qu 等4人

3

基于折扣活性公式的操作策略离线评估 Offline Policy Evaluation for Manipulation Policies via Discounted Liveness Formulation

Hao Wang, Joshua Bowden, Colton Crosby 等4人

4

协调扩散：无需多智能体演示即可生成多智能体行为 Coordinated Diffusion: Generating Multi-Agent Behavior Without Multi-Agent Demonstrations

Lasse Peters, Laura Ferranti, Javier Alonso-Mora 等4人

5

PRISM：在模拟具身环境中进行意图驱动的规划与推理 PRISM: : Planning and Reasoning with Intent in Simulated Embodied Environments

Yunn Kang Lim, Pengzhan Sun, Ziyi Bai 等7人

6

RIO：面向跨具身机器人学习的灵活实时机器人输入/输出 RIO: Flexible Real-Time Robot I/O for Cross-Embodiment Robot Learning

Pablo Ortega-Kral, Eliot Xing, Arthur Bucker 等16人

7

基于采样的机械臂安装连续体机器人跟随领导者运动规划 Sampling-Based Follow-the-Leader Motion Planning for Manipulator-Mounted Continuum Robots

Chengnan Shentu, Nicholas Baldassini, Oluwagbotemi D. Iseoluwa 等5人

8

基于原型语义部件发现的天气鲁棒跨视角地理定位 Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery

Chi-Nguyen Tran, Dao Sy Duy Minh, Huynh Trung Kiet 等6人

9

鹦鹉螺：从单一提示到即插即用的机器人学习 Nautilus: From One Prompt to Plug-and-Play Robot Learning

Yufeng Jin, Jianfei Guo, Xiaogang Jia 等11人

10

四足机器人状态估计的仅本体感觉基准：滤波器与平滑器在ATE、RPE和运行时之间的权衡 A Proprioceptive-Only Benchmark for Quadruped State Estimation: ATE, RPE, and Runtime Trade-offs Between Filters and Smoothers

Ylenia Nisticò, João Carlos Virgolino Soares, Joan Solà 等4人

11

基于运动学感知设计的彩虹深度Q学习用于协作Delta和3-RRS并联机器人插入 Rainbow Deep Q-Learning with Kinematics-Aware Design for Cooperative Delta and 3-RRS Parallel Robot Insertion

Hassen Nigatu, Gaokun Shi, Jituo Li 等5人

12

使用软体夹爪将环境约束引入到抓取纸类柔性材料的策略中 Introducing Environmental Constraints to Grasping Strategies for Paper-Like Flexible Materials Using a Soft Gripper

Yi Dong, Yang Li, Jinjun Duan 等4人

13

DreamAvoid: 关键阶段测试时模拟以避免VLA策略中的失败 DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies

Xianzhe Fan, Yuxiang Lu, Shenyuan Gao 等7人

14

NavOL：在线模仿学习的导航策略 NavOL: Navigation Policy with Online Imitation Learning

Xiaofei Wei, Chun Gu, Li Zhang

15

关注要点：面向可泛化视觉-语言-动作模型的可微分网格采样剪枝 See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model

Yixu Feng, Zinan Zhao, Yanxiang Ma 等7人

16

人形机器人上的具身情感触觉策略映射 Mapping Embodied Affective Touch Strategies on a Humanoid Robot

Qiaoqiao Ren, Omar Eldardeer, Francesca Cocchella 等6人

17

利用多视角潜在先验学习机器人操作的动作流形 Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation

Junjin Xiao, Dongyang Li, Yandan Yang 等12人

18

EvoNav: 基于大语言模型的机器人导航进化奖励函数设计 EvoNav: Evolutionary Reward Function Design for Robot Navigation with Large Language Models

Zhikai Zhao, Chuanbo Hua, Federico Berto 等7人

19

从反应到预见：基于智能体任务图的机器人操作主动故障恢复 From Reaction to Anticipation: Proactive Failure Recovery through Agentic Task Graph for Robotic Manipulation

Sheng Xu, Ruixing Jin, Huayi Zhou 等9人

20

集体感知增强的协作机器人用于交通调节 Cooperative Robotics Reinforced by Collective Perception for Traffic Moderation

Mohammad Khoshkdahan, John Pravin Arockiasamy, Andy Flores Comeca 等4人