cs.RO（2026-10-09）

📊 共 40 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (30 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (7) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (30 篇)

#题目一句话要点标签🔗⭐
1 PartiGen: Part-Aware Representations for Language-Conditioned Humanoid Motion Generation 提出PartiGen以解决语言驱动的人形运动生成问题 humanoid Unitree motion generation
2 Evo-World: A Lightweight Vision-Language-Action Model with Future Motion Prediction via Optical-Flow Supervision 提出Evo-World以解决视觉-语言-动作模型的未来运动预测问题 manipulation bi-manual bimanual manipulation
3 VICAR: Video Imitation with Contact-Aware Retargeting for Humanoid Interactive Skills 提出VICAR以解决人形机器人模仿中的接触感知问题 humanoid manipulation loco-manipulation
4 Splat2Act: From Captured Scenes to Personalized VLA Manipulation 提出Splat2Act以解决个性化VLA操作问题 manipulation sim-to-real 3D gaussian splatting
5 AutoBio+: Benchmarking Dexterous Manipulation with Dynamic Experimental Phenomena in Realistic Laboratories 提出AutoBio+以解决生物实验室中灵巧操作的评估问题 manipulation dexterous manipulation sim-to-real ✅
6 JitterVLA: A Replay Benchmark for Motion Quality in VLA-Driven Human-Robot Manipulation 提出JitterVLA以解决VLA驱动人机操作中的运动质量问题 manipulation human motion vision-language-action
7 Adaptive Whole-Body MPC with Optimal Posture Planning for Humanoid Robots under Unknown Payloads 提出自适应全身MPC以应对未知负载下的平衡问题 humanoid humanoid robot whole-body control
8 Beyond Actions: Learning Future Operation Targets for Vision-Language-Action Models 提出AFCE以解决视觉-语言-动作模型的未来目标预测问题 manipulation dexterous manipulation bi-manual ✅
9 Belief-Overlap Partial Inversion: Object-Centric Flow Replanning for Humanoid Loco-Manipulation 提出Belief-Overlap Partial Inversion以解决人形机器人推物体的规划问题 humanoid whole-body control manipulation
10 ATHLETE: Learning Reactive Humanoid Tennis via Trajectory-Guided Motion Matching 提出ATHLETE框架以解决人形机器人网球反应协调问题 humanoid humanoid robot locomotion
11 Grounded-Dreamer: Robot Learning from World Model Synthetic Data with Physical Grounding 提出Grounded-Dreamer以解决机器人操作数据收集难题 manipulation teleoperation policy learning
12 Noise Space Learning for VLA Adaptation 提出噪声空间学习以适应视觉-语言-动作模型 manipulation PPO SAC
13 JoyInside-VLM-Agent: Product-Conditioned Multimodal Policy Learning for Embodied Agents 提出JoyInside-VLM-Agent以解决多模态执行与产品约束问题 quadruped reinforcement learning policy learning
14 VLMs are Native Action Models: Unleashing the Manipulation Capabilities of VLMs with Explicit Action-Space Grounding 提出EASG框架以解决VLM在机器人操作中的应用问题 manipulation vision-language-action VLA
15 EgoReveal: Learning Active Vision and Object Manipulation under Partial Occlusions from Egocentric Demonstrations 提出EgoReveal以解决部分遮挡下的主动视觉与物体操控问题 manipulation teleoperation egocentric
16 RARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic Manipulation 提出RARA以解决机器人操作任务中的策略微调问题 manipulation diffusion policy vision-language-action ✅
17 Dual-Stream Memory for Vision-Language-Action Policies 提出双流记忆机制以解决视觉-语言-动作策略中的状态跟踪问题 manipulation policy learning vision-language-action
18 PATACON: GPU-Parallel Tangent-Bundle RRT-Connect for Constrained Motion Planning 提出PATACON以解决高维约束运动规划问题 humanoid humanoid robot dual-arm
19 TAME-Nav: Temporal Asymmetric Mixture-of-Experts Distillation for Agile and Versatile Robot Navigation 提出TAME-Nav以解决机器人导航中的决策多样性问题 quadruped sim-to-real domain randomization
20 Sampling-based Kinodynamic Planning with World Models 提出基于采样的动力学规划方法以解决长时间任务的优化问题 motion planning world model world models
21 Human2Dex: Dexterous Robot Learning from Wrist-Centric Human Demonstrations 提出Human2Dex以解决机器人手灵巧操作数据收集问题 manipulation dexterous hand dexterous manipulation
22 Evo-RL: Iterative Robot Reinforcement Learning from Selective Experience 提出Evo-RL以解决机器人强化学习中的经验选择问题 manipulation reinforcement learning
23 SmolWAM: A Latent World-Action Model for Robotic Manipulation on Edge Devices 提出SmolWAM以解决边缘设备上机器人操作的计算效率问题 manipulation
24 Mapless, Stabilizing, and Anti-Stuck Flipper Control for Articulated Tracked Robots 提出无地图、稳定和防卡滞的翻转控制方法以解决机器人运动问题 teleoperation elevation map
25 Low-Latency Mapless ESDF Queries for MAV Reactive Collision Avoidance 提出无地图的低延迟ESDF查询以解决MAV反应式避障问题 MPC model predictive control
26 ReAT: Residual Action Tokenization for Autoregressive Robot Policies 提出残差动作标记化方法以提升自回归机器人策略的性能 manipulation policy learning
27 BT-Agent: Deploying Onboard Robot Agents with Behavior Trees and Multi-Fidelity Evaluation 提出BT-Agent以解决移动机器人任务执行中的计算限制问题 quadruped
28 Towards a Unified Taxonomy of Agricultural Harvesting Technologies: Linking Physical Interaction, Automation, and Selectivity 提出统一分类法以解决农业收获技术的比较问题 manipulation
29 Cooperative Aerial Transportation of a Payload with a Sliding Cable Attachment 提出双四旋翼钩挂运输系统以解决非刚性负载的空中协作问题 manipulation
30 Robot-WATCHDOG : failure detection through object-centric graph representation 提出Robot-WATCHDOG以解决机器人故障检测问题 manipulation ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
31 Reflect-VLA: Internalizing Reflective Guidance via Dual-Path On-Policy Self-Distillation for Autonomous Driving 提出Reflect-VLA以解决自主驾驶中的规划错误诊断问题 reinforcement learning distillation privileged information
32 Beyond Successful Robot Demonstrations: Learning from Human Interactions and Modeling Failure Dynamics 提出HF-WM以解决机器人交互与失败动态建模问题 world model world models egocentric
33 Dream to Remember: Continual Steering of Generalist Robot Policies with World Models 提出Dream to Remember以解决机器人策略持续学习问题 reinforcement learning imitation learning world model
34 LeapBot-JAC: Joint Action Chains for World Action Models 提出LeapBot-JAC以解决固定动作令牌预算下的执行问题 world model world models world action model
35 Forward Dynamics Models 提出前向动力学模型以解决机器人动作预测问题 policy learning world action model world action models
36 CeDR-Nav: Cross-Embodiment Mapless Navigation via Offline Demonstration Recasting 提出CeDR-Nav以解决跨实体无图导航问题 DRL cross-embodiment
37 Evidence-Guided Counterfactual Learning for Long-Tailed Robotic Policies 提出证据引导的反事实学习以解决长尾机器人策略问题 policy learning VLA

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
38 HorizonNav: Geometry-Guided Video Diffusion for Anticipatory 3D Robot Navigation 提出HorizonNav以解决机器人导航中的几何一致性问题 Depth Anything geometric consistency
39 When LiDAR Fades, Radar Takes Over: LiDAR Reliability-Aware Adaptive Localization Under Airborne Obscurants 提出一种基于雷达的自适应定位方法以应对LiDAR可靠性下降问题 LIO

🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)

#题目一句话要点标签🔗⭐
40 RESCUE: Is This Alarm Worth Acting On? Counterfactual Evaluation of VLA Runtime Monitors 提出RESCUE框架以评估机器人监控警报的有效性 VLA OpenVLA

⬅️ 返回 cs.RO 首页 · 🏠 返回主页