cs.RO（2026-11-03）

📊 共 37 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (27 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (2)

🔬 支柱一：机器人控制 (Robot Control) (27 篇)

#题目一句话要点标签🔗⭐
1 Online iLQR-MPC with Whole-Body Control for Robust Humanoid Locomotion 提出在线iLQR-MPC方法以解决鲁棒人形机器人步态控制问题 humanoid humanoid locomotion whole-body control
2 HLO-AMP: Hierarchical Loco-Manipulation from Object-Aware Motion Priors 提出HLO-AMP框架以解决人形机器人操控中的物体动态问题 humanoid whole-body control WBC
3 ReflexArc: Bottom-Up Integration of Instantaneous Tactile Reflexes into Whole-Body Humanoid Control 提出ARC框架以解决类人机器人瞬时触觉反射控制问题 humanoid humanoid robot humanoid control ✅
4 PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations 提出PrimeSim以解决机器人世界模型模拟中的一致性和长时间预测问题 manipulation world model world models
5 CRONOS: Benchmarking Non-Episodic Reinforcement Learning for Robotic Manipulation 提出CRONOS以解决非情节强化学习在机器人操作中的挑战 manipulation reinforcement learning embodied AI ✅
6 Caging Vision-Language Navigation for Legged Robots via Barrier-Certified Safety Architecture 提出基于安全架构的腿部机器人视觉语言导航方法 quadruped legged robot humanoid
7 Coordinating Humanoid Loco-Manipulation through Action-Conditioned Latent Foresight 提出动作条件潜在前瞻模型以解决类人机器人协调运动问题 humanoid manipulation loco-manipulation ✅
8 RoboTryOn: Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On 提出RoboTryOn以解决高自由度机器人演示生成问题 humanoid manipulation bi-manual
9 All-For-One: Distilling Visual Foundation Models to a Fast, Memory-Efficient Visuomotor Policy 提出All-For-One框架以高效蒸馏视觉基础模型用于机器人控制 manipulation representation learning distillation
10 Physical Diffusion Policy via MPM-Guided 3D Gaussian Simulation 提出物理扩散策略以解决多样物体操控问题 manipulation imitation learning diffusion policy
11 Should the Action Expert Train the VLM? Action-Token Supervision and Gradient Routing in Mixture-of-Transformer VLAs 提出动作令牌监督与梯度路由以优化VLA模型训练 manipulation flow matching vision-language-action
12 ActOR: Ambient AI-Based Agentic Orchestration for Humanoid Autonomy in Operating Rooms 提出ActOR以解决手术室中人形机器人自主性问题 humanoid humanoid robot locomotion
13 Spectrally Routed Diffusion Policy for Multi-Task Robotic Manipulation 提出光谱路由扩散策略以解决多任务机器人操作问题 manipulation bi-manual diffusion policy
14 DexHOT: Learning Hand-Object Configuration Transfer for Dexterous Manipulation 提出DexHOT以解决灵巧操作中的手-物体配置转移问题 manipulation dexterous hand dexterous manipulation ✅
15 RAFT: Reasoning-Aligned Fine-Tuning Improves Robustness of VLA Post-Training 提出RAFT以提升VLA后训练的鲁棒性 bi-manual vision-language-action VLA
16 Action Intent as a Bridge: Transferring Manipulation Knowledge from Human-Centric Videos to Robots 提出行动意图转移方法以解决机器人操作知识转移问题 manipulation vision-language-action VLA
17 Asynchronous Robot Policies 提出异步机器人策略以解决实时反应能力不足问题 manipulation vision-language-action VLA
18 HiLo-WAM: Decoupling Long-Horizon Task Evolution and Local Dynamics in World Action Models 提出HiLo-WAM以解决长时间任务演变与局部动态耦合问题 manipulation world action model world action models
19 RAIPAL: A Powerful and Agile Humanoid Arm for Human Tasks 提出RAIPAL以实现人类任务的高效执行 humanoid human-to-humanoid
20 GUILD: Guided Iterative Data Collection for Imitation Learning 提出GUILD以解决模仿学习中的数据收集效率问题 teleoperation imitation learning
21 Haptic Shared Control for Multi-Robot Systems 提出触觉共享控制以优化多机器人系统的协作 shared control
22 Do Agentic Policies Need to Look at Every Step? Geometric Abstraction for Reasoning and Action 提出几何抽象方法以优化机器人多步操作推理 manipulation multimodal
23 PACT: Pose-Robust Actuation Co-Design for Tendon-Driven Robotic Hands 提出PACT框架以解决人形机器人手的驱动设计问题 humanoid humanoid robot
24 WayTrace: A Map-to-Language-to-Trace Hierarchy for Embodied Urban Navigation 提出WayTrace以解决自主机器人导航中的指令执行问题 legged robot reinforcement learning
25 PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data 提出PyRUA-DataFarm以降低机器人数据收集成本 teleoperation
26 Nested Field-of-View Barriers for Teleoperated Multi-Robot Relay Chains 提出共享自主框架以解决多机器人远程操作中的通信问题 teleoperation
27 Grasping and Stabilizing Tumbling Objects with Rotating-Base Multi-Arm Space Manipulators 提出一种新方法以稳定翻滚物体的多臂空间操控器 motion planning

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
28 Trusting Imagined Futures: Auditing Imagined Rewards for VLA Post-Training 提出Trusting Imagined Futures以解决VLA后训练中的奖励审计问题 behavior cloning world model world models
29 Future Representation Distillation for Imagination-Free World Action Models 提出DreamFree以解决机器人控制中的视频预测问题 world action model world action models distillation
30 PolicyIK: High-Precision Inverse Kinematics for Robot Arms with Reinforcement Learning 提出PolicyIK以解决机器人臂高精度逆向运动学问题 reinforcement learning PPO cross-embodiment ✅
31 Hybrid Particle-Voxel Dynamics for Multimodal 3D World Simulation 提出混合粒子-体素动态以解决多模态3D世界模拟问题 policy learning world model world models
32 Trajectory Evaluation via Rollout-Free World Model for End-to-end Autonomous Driving 提出RFWorld以解决自主驾驶轨迹评估中的高成本问题 world model world models
33 GSBR: Geometric Support Behavior Regularization for Online RL 提出GSBR以解决在线强化学习的样本效率问题 reinforcement learning imitation learning flow matching ✅
34 LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation 提出ARPG框架以解决自动化机器人策略生成问题 reinforcement learning large language model
35 Safeguarding Multi-Agent Reinforcement Learning for Connected and Automated Vehicles with Recursively Feasible Control Barrier Functions 提出备份地平线控制屏障函数以保障多智能体强化学习的安全性 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
36 LoopQ: Fair, Closed-Loop Evaluation of Quantized Vision-Language-Action Models 提出LoopQ以实现量化视觉-语言-动作模型的公平闭环评估 vision-language-action VLA OpenVLA
37 DiMuRe: Diagnosis-Guided Multilevel Recovery for Robotic Task Execution 提出DiMuRe框架以解决机器人任务执行中的干扰问题 vision-language-action VLA large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页