End-to-end Learning for Multi-Embodiement Locomotion
The rapid development of robotics has enabled legged robots capable of performing highly dynamic tasks such as walking ...
Engineering Sciences
Computer Science
Related Projects as Principal Investigator
-
Learning Interpretable Representations for Visuotactile Sensors
Visuotactile sensors are gaining momentum in robotics because they provide high-resolution contact measurements at a ...
Engineering Sciences
Learning to Plan
Motion planning is a crucial component of autonomous robot systems. It addresses the problem of finding a feasible ...
Engineering SciencesComputer Science
Metric Self-Paced Reinforcement Learning
Reinforcement Learning (RL) is a promising tool for solving complicated control and decision-making tasks in a data ...
Engineering SciencesComputer Science
Policy Optimization with Learning and Planning in Continuous Spaces
Planning algorithms have shown impressive performance in many domains such as chess and Go. In particular, Monte Carlo ...
Engineering SciencesComputer Science
Active Exploration for Robotic Manipulation
Robotic manipulation stands as a largely unsolved problem despite significant advances in robotics and machine learning ...
Engineering SciencesComputer Science
Adaptive Autonomous Assembly
Autonomous robotic assembly requires a well-orchestrated sequence of high-level actions and smooth manipulation ...
Engineering SciencesComputer Science
Gradient-Based Variational Inference by Policy Search
In variational inference, we want to approximate an intractable target distribution (often given as a posterior ...
Engineering SciencesComputer Science-
Learning for Decentralized, Long-Horizon Manipulation
Achieving long-horizon dexterous manipulation remains a challenging problem in robotics. There exists a long history of ...
Engineering SciencesSystems Engineering 
Distributionally Robust Trajectory Optimization Under Uncertain Dynamics via Relative-Entropy Trust Regions
Trajectory optimization and model predictive control are essential techniques underpinning advanced robotic applications ...
Engineering SciencesComputer Science
Learning Physically Interactive Behaviours for Human-Robot Interaction
Modeling interaction dynamics to generate robot trajectories that enable a robot to adapt and react to a human’s actions ...
Engineering SciencesComputer Science
Measure-Valued Derivatives for Reinforcement Learning
Reinforcement learning methods for robotics are increasingly successful due to the constant development of better policy ...
Engineering SciencesComputer Science
When to Trust Your Model in Model-based Value Expansion?
Model-based value expansion methods promise to improve the quality of value function targets and, thereby, the ...
Engineering SciencesComputer Science
Balloon Estimators for Improving and Scaling the Nonparametric Off-Policy Policy Gradient
The Nonparametric Off-Policy Policy Gradient (NOPG) is a policy gradient algorithm to solve reinforcement learning tasks ...
Engineering SciencesComputer Science-
Evaluating and Improving Recurrent Kalman Networks
Precise models of the system dynamics are crucial for model-based control and reinforcement learning (RL) in autonomous ...
Engineering SciencesComputer Science -
Model Learning With Recurrent Kalman Networks
Recurrent State-space models (RSSMs) are highly expressive models for learning patterns in time series data and system ...
Engineering SciencesComputer Science -
Stochastic Search for Applications in Robotics
Stochastic-search algorithms are problem independent algorithms well-suited for black-box optimization of an objective ...
Engineering SciencesComputer Science -
Deep Reinforcement Learning under Uncertainty
Traditionally robots have been used in factories in predefined structured environments. Recently, robots are employed ...
Engineering SciencesComputer Science 
Robot Skill Learning
The project investigated probabilistic motor skill learning for simulated robots. In detail the project looked into the ...
Engineering SciencesComputer Science
