cs.RO（2025-02-05）

📊 共 17 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (13 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#	题目	一句话要点	标签	🔗	⭐
1	A Unified and General Humanoid Whole-Body Controller for Versatile Locomotion	提出HugWBC：一种通用的人形机器人全身控制器，实现多功能运动	humanoid humanoid robot humanoid control
2	Gait-Net-augmented Implicit Kino-dynamic MPC for Dynamic Variable-frequency Humanoid Locomotion over Discrete Terrains	提出Gait-Net增强的隐式运动动力学MPC，用于动态变频人形机器人跨越离散地形的步态控制。	humanoid humanoid locomotion locomotion
3	HiLo: Learning Whole-Body Human-like Locomotion with Motion Tracking Controller	HiLo：基于运动跟踪控制器的全身人形机器人拟人运动学习	humanoid humanoid robot whole-body control
4	Contact-Aware Motion Planning Among Movable Objects	提出接触感知运动规划（CAMP）方法，解决移动机器人与可移动物体交互问题	locomotion motion planning contact-aware
5	Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation	提出基于信息瓶颈的行为克隆方法，提升机器人操作泛化性	manipulation imitation learning behavior cloning	✅
6	SPARK: Safe Protective and Assistive Robot Kit	SPARK：安全、保护和辅助机器人工具包，保障人型机器人自主与遥操作安全	humanoid humanoid robot teleoperation	✅
7	Dexterous Safe Control for Humanoids in Cluttered Environments via Projected Safe Set Algorithm	提出p-SSA算法，解决复杂环境下人型机器人灵巧安全控制问题	humanoid humanoid robot Unitree
8	UMC: Unified Resilient Controller for Legged Robots with Joint Malfunctions	提出UMC：一种用于关节故障腿式机器人的统一鲁棒控制器	legged robot locomotion
9	Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models	提出SMD，结合约束优化与扩散模型，解决多机器人运动规划难题	motion planning
10	RoboGrasp: A Universal Grasping Policy for Robust Robotic Control	RoboGrasp：一种通用的抓取策略，用于鲁棒的机器人控制	manipulation imitation learning world model
11	Kineto-Dynamical Planning and Accurate Execution of Minimum-Time Maneuvers on Three-Dimensional Circuits	提出基于Kineto-Dynamical模型的自动驾驶赛车手，用于三维赛道最小时间机动规划与精确执行。	model predictive control
12	Implicit Communication in Human-Robot Collaborative Transport	提出一种基于隐式通信的人机协作搬运框架，提升协作流畅性和效率。	model predictive control
13	Global Contact-Rich Planning with Sparsity-Rich Semidefinite Relaxations	提出基于稀疏半定松弛的全局接触丰富运动规划方法	motion planning

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
14	The Temporal Trap: Entanglement in Pre-Trained Visual Representations for Visuomotor Policy Learning	针对视觉运动策略学习，提出解耦预训练视觉表征时序纠缠的方法	policy learning
15	Conditional Prediction by Simulation for Automated Driving	提出基于交通仿真的条件预测模型，实现自动驾驶车辆的协同规划	reinforcement learning inverse reinforcement learning	✅
16	Learning Efficient Flocking Control based on Gibbs Random Fields	提出基于吉布斯随机场的MARL框架，解决拥堵环境中多机器人高效集群控制问题。	reinforcement learning reward design

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
17	GARAD-SLAM: 3D GAussian splatting for Real-time Anti Dynamic SLAM	GARAD-SLAM：面向动态环境的实时3D高斯溅射SLAM系统	3D gaussian splatting 3DGS gaussian splatting

⬅️ 返回 cs.RO 首页 · 🏠 返回主页