Projects
Robot Learning for Unexpected Behaviour Detection and Introspection
A CV-based research aimed for providing on high precision motion prediction for Under-Actuated robots.
Computer VisionROAWorld ModelLatent EstimationDreamercurrent
Quality-Diversity Reinforcement Learning for Damage Recovery in Robotics
A QD reinforcement learning-based research to enable robots to recover from unexpected damages with better performance and significantly less trials.
Robotic LocomotionReinforcement LearningJAXAIlatest
Driving Condition-based Energy Management Strategy of Hybrid Vehicles
A reasearch on driving profile aware energy management strategy that achieves lower energy consumption of hybrid electric vehicles.
Multi-agentDDPGTCN ForcastingPytorch
VAE-Based Driving Profile Generation Algorithms
Developed a model for generating realistic driving condition scenarios using variational autoencoders to simulate diverse traffic patterns.
VAELSTMTemporal embeddings