Publications

Optimal Transport Policy Fusion for Learning Diverse Skills
Articulated Object Interaction in Unknown Scenes with Whole-Body Mobile Manipulation.
Modular Action Concept Grounding in Semantic Video Prediction
Bayesian Optimisation for Robust Model Predictive Control under Model Parameter Uncertainty
Parallelised Diffeomorphic Sampling-based Motion Planning
CLIPort: What and Where Pathways for Robotic Manipulation
Trajectory Generation in New Environments from Past Experiences
Towards Coordinated Robot Motions: End-to-End Learning of Motion Policies on Transform Trees
Probabilistic Trajectory Prediction with Structural Constraints
PlannerFlows: Learning Motion Samplers with Normalising Flows
Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos
Value Iteration in Continuous Actions, States and Time.
Coach-Player Multi-agent Reinforcement Learning for Dynamic Team Composition.

🏆 Long Talk

A differentiable simulator for robotic cutting
Reactive Human-to-Robot Handovers of Arbitrary Objects

🏆 Best Paper Award on Human-Robot Interaction

Object Rearrangement Using Learned Implicit Collision Functions
LEAF: Latent Exploration Along the Frontier.
Generalized Nonlinear and Finsler Geometry for Robotics
Fast Uncertainty Quantification for Deep Object Pose Estimation
Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects
Dynamics Randomization Revisited: A Case Study for Quadrupedal Locomotion
Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes
Anticipatory Navigation in Crowds by Probabilistic Prediction of Pedestrian Future Movements
ACRONYM: A Large-Scale Grasp Dataset Based on Simulation
Curriculum By Smoothing

🏆 Spotlight

Counterfactual Data Augmentation using Locally Factored Dynamics

🏆 Outstanding Paper Award at OOL Workshop at ICML 2020

Stein Variational Model Predictive Control
A User's Guide to Calibrating Robotics Simulators
Online BayesSim for Combined Simulator Parameter Inference and Policy Improvement
Multi-Fingered Active Grasp Learning
Human Grasp Classification for Reactive Human-to-Robot Handovers
Collaborative Interaction Models for Optimized Human-Robot Teamwork
6-DOF Grasping for Target-driven Object Manipulation in Clutter

🏆 Finalist for Best Student Paper Award and Best Paper in Robot Manipulation

Combining Model-Free and Model-Based Strategies for Sample-Efficient Reinforcement Learning

🏆 Best Workshop Paper Award

The CoSTAR Block Stacking Dataset: Learning with Workspace Constraints
Scaling Robot Supervision to Hundreds of Hours with RoboTurk: Robotic Manipulation Dataset through Human Reasoning and Dexterity

🏆 Best Cognitive Science Paper Award Finalist

Representing Robot Task Plans as Robust Logical-Dynamical Systems
Learning to Plan Hierarchically from Curriculum
Early Fusion for Goal Directed Robotic Vision

🏆 IROS RoboCup Best Paper Award Finalist

Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning
ContactGrasp: Functional Multi-finger Grasp Synthesis from Contact
Conditional Driving from Natural Language Instructions
Predictor Corrector Policy Optimization
Bayesian Deconditional Kernel Mean Embeddings