CoRL 2025

195 papers

Top Research Directions

Research directions most represented by CoRL 2025 papers.

Scaling Robotic Learning Beyond Expert Demonstrations 15
Zero-Shot Sim-to-Real Transfer for Robotic Control 9
Bridging the Embodiment Gap in Robot Learning 6
Privileged Information Distillation for Sim-to-Real Policy Transfer 5
Scaling Robotic Control to Long-Horizon Multi-Stage Tasks 5
The Reward Engineering Bottleneck in Reinforcement Learning 5
3D Gaussian Splatting for Photorealistic Scene Representation 4
Integrating Social Norms into Robot Motion Planning 3
Scaling Robot Learning with Physics-Informed Synthetic Data 3
Model Free Generalizable 6D Object Pose Estimation 3
Motion Planning Beyond the Static Environment Assumption 3
Overcoming Visual Self Occlusion in Robotic Manipulation 3
Overcoming the Reality Gap in Robotic Control 3
Generalizing Robot Learning Beyond Pick and Place 2
Optimization through Discontinuous Contact Dynamics 2

Top Authors

AuthorPapers
Marco Hutter6
Sergey Levine5
Yuke Zhu5
Byron Boots4
Daniel Seita4
David Held4
Dieter Fox4
Guillaume Adrien Sartoretti4
Jeannette Bohg4
Mac Schwager4
Xiaolong Wang4
Ziwei Wang4
Abhishek Gupta3
Animesh Garg3
Anirudha Majumdar3
Anxing Xiao3
Chelsea Finn3
Chen Tang3
David Hsu3
Hao Dong3

Impactful Papers

Papers from CoRL 2025 that shaped research clusters.

Influential

Papers

Title
RoboChemist: Long-Horizon and Safety-Compliant Robotic Chemical Experimentation
Robot Learning from Any Images
Robot Operating Home Appliances by Reading User Manuals
RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning
Robust Dexterous Grasping of General Objects
SafeBimanual: Diffusion-based trajectory optimization for safe bimanual manipulation
Sampling-based System Identification with Active Exploration for Legged Sim2Real Learning
SAVOR: Skill Affordance Learning from Visuo-Haptic Perception for Robot-Assisted Bite Acquisition
ScrewSplat: An End-to-End Method for Articulated Object Recognition
SDS – See it, Do it, Sorted: Quadruped Skill Synthesis from Single Video Demonstration
Search-TTA: A Multi-Modal Test-Time Adaptation Framework for Visual Search in the Wild
See, Point, Fly: A Learning-Free VLM Framework for Universal Unmanned Aerial Navigation
Self-supervised perception for tactile skin covered dexterous hands
Sequence Modeling for Time-Optimal Quadrotor Trajectory Optimization with Sampling-based Robustness Analysis
Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation
Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids
SIREN: Semantic, Initialization-Free Registration of Multi-Robot Gaussian Splatting Maps
SocialNav-SUB: Benchmarking VLMs for Scene Understanding in Social Robot Navigation
“Stack It Up!”: 3D Stable Structure Generation from 2D Hand-drawn Sketch
Steerable Scene Generation with Post Training and Inference-Time Search
Steering Your Diffusion Policy with Latent Space Reinforcement Learning
Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories
Subteaming and Adaptive Formation Control for Coordinated Multi-Robot Navigation
Tactile Beyond Pixels: Multisensory Touch Representations for Robot Manipulation
Text2Touch: Tactile In-Hand Manipulation with LLM-Designed Reward Functions
The Sound of Simulation: Learning Multimodal Sim-to-Real Robot Policies with Generative Audio
ToddlerBot: Open-Source ML-Compatible Humanoid Platform for Loco-Manipulation
TopoCut: Learning Multi-Step Cutting with Spectral Rewards and Discrete Diffusion Policies
Toward Real-World Cooperative and Competitive Soccer with Quadrupedal Robot Teams
Towards Generalizable Safety in Crowd Navigation via Conformal Uncertainty Handling
Training Strategies for Efficient Embodied Reasoning
Train-Once Plan-Anywhere Kinodynamic Motion Planning via Diffusion Trees
TReF-6: Inferring Task-Relevant Frames from a Single Demonstration for One-Shot Skill Generalization
TWIST: Teleoperated Whole-Body Imitation System
TypeTele: Releasing Dexterity in Teleoperation by Dexterous Manipulation Types
Uncertainty-aware Accurate Elevation Modeling for Off-road Navigation via Neural Processes
UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations
UniTac2Pose: A Unified Approach Learned in Simulation for Category-level Visuotactile In-hand Pose Estimation
UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation
Unsupervised Skill Discovery as Exploration for Learning Agile Locomotion
Visual Imitation Enables Contextual Humanoid Control
VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision
VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning
Wheeled Lab: Modern Sim2Real for Low-cost, Open-source Wheeled Robotics
ZipMPC: Compressed Context-Dependent MPC Cost via Imitation Learning

« prev Page 4/4