Henrik I Christensen

Latest

• BridgeSim: Unveiling the OL-CL Gap in End-to-End Autonomous Driving
• DexFLEX: Contact-Aware Foundation Controller for Command-Guided Dexterity
• FlashRFCL: Demonstration-Efficient Sparse Reward RL via Reverse-Forward Curriculum Learning in High-Throughput GPU Simulation
• Sensitivity Shaping for Latent Modeling
• GLIDE: A Coordinated Aerial-Ground Framework for Search and Rescue in Unknown Environments
• Scaling Cross-Embodiment World Models for Dexterous Manipulation
• Controllable Motion Generation via Diffusion Modal Coupling
• ROSCOE: Robot Scanning and Computing Equipment for Autonomous Terrestrial Mapping
• Merging and Disentangling Views in Visual Reinforcement Learning for Robotic Manipulation
• Learning Dexterous Deformable Object Manipulation Through Cross-Embodiment Dynamics Learning
• Towards Embodiment Scaling Laws in Robot Locomotion
• Learning Dexterous Deformable Object Manipulation Through Cross-Embodiment Dynamics Learning
• Towards Embodiment Scaling Laws in Robot Locomotion
• OSM vs HD Maps: Map Representations for Trajectory Prediction
• Motion Planning in Foliated Manifolds using Repetition Roadmap
• TridentNet: A Conditional Generative Model for Dynamic Trajectory Generation
• Towards Lifelong Adaptive Agents: Using Meta- reasoning for Combining Task Planning and Situated Learning
• Distributed mapping with privacy and communication constraints: Lightweight algorithms and object-based models