cs.RO（2025-10-05）

📊 共 10 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (8) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (8 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Stability-Aware Retargeting for Humanoid Multi-Contact Teleoperation	提出基于质心稳定性的重定向方法，增强人型机器人遥操作的稳定性。	humanoid humanoid robot manipulation
2	Flexible Locomotion Learning with Diffusion Model Predictive Control	提出Diffusion-MPC，利用扩散模型预测控制实现腿式机器人灵活运动学习。	legged locomotion locomotion MPC
3	From Shadow to Light: Toward Safe and Efficient Policy Learning Across MPC, DeePC, RL, and LLM Agents	提出八种方法以提升数据驱动控制策略的安全性与效率	MPC model predictive control reinforcement learning
4	VBM-NET: Visual Base Pose Learning for Mobile Manipulation using Equivariant TransporterNet and GNNs	VBM-NET：利用等变TransporterNet和GNN学习移动操作的视觉基座位姿	manipulation mobile manipulation sim-to-real
5	Learning to Capture Rocks using an Excavator: A Reinforcement Learning Approach with Guiding Reward Formulation	提出基于强化学习的挖掘机抓取石块方法，无需显式建模。	manipulation domain randomization reinforcement learning
6	SITCOM: Scaling Inference-Time COMpute for VLAs	SITCOM：通过扩展推理时计算能力提升VLA模型在机器人控制中的性能	real2sim model predictive control vision-language-action
7	Reliable and Scalable Robot Policy Evaluation with Imperfect Simulators	提出SureSim框架以解决机器人策略评估的可靠性问题	manipulation imitation learning diffusion policy
8	Integrated Planning and Control on Manifolds: Factor Graph Representation and Toolkit	提出FactorMPC：基于因子图的流形上集成规划与控制工具包	MPC model predictive control motion planning

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
9	ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context	ContextVLA：通过分摊多帧上下文的视觉-语言-动作模型，提升机器人任务性能。	behavior cloning vision-language-action VLA

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

#	题目	一句话要点	标签	🔗	⭐
10	Zenbo Patrol: A Social Assistive Robot Based on Multimodal Deep Learning for Real-time Illegal Parking Recognition and Notification	提出基于多模态深度学习的Zenbo巡逻机器人，用于实时识别和通知违章停车。	multimodal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页