Robotics

Our robotics research focuses on applying our advances in reinforcement learning and computer vision to real-world robotic systems.

  • Mobile Vehicles
  • Autonomous Vehicle System
  • Manipulators (Robot Arms)
  • Manufacturing System
Robotics

Deep Learning Vision

We focus on developing robust and efficient vision systems for robots, enabling them to understand and interact with their environment effectively.

Perception

  • Semantic Segmentation
  • Depth Estimation
  • Object Detection
  • Panoptic Segmentation
Perception

Robust Vision

  • Image Restoration
  • Domain Adaptation
  • Domain Generalization
Robust Vision

Efficient Vision

  • Multi-Task Learning
  • Knowledge Distillation
Efficient Vision

End-to-End Driving

Our end-to-end driving research aims to learn robust driving policies directly from multi-modal sensor inputs for real-world autonomous navigation.

  • End-to-End Policy Learning
  • Safety-Aware Driving
  • Multi-Modal Fusion (Camera / LiDAR / IMU)
  • Sim-to-Real Transfer
End-to-end autonomous driving

Reinforcement Learning

Our research in reinforcement learning focuses on developing intelligent agents that can follow the expert behavior.

Imitation Learning

  • Behavior Cloning
  • Offline RL
  • Inverse RL
Imitation Learning

Embodied AI

  • Cross Embodiment
  • Domain Randomization
  • Model Approximation
Embodied AI