Institute Homepage
Institute Homepage Sign In

Back

Research Overview

Intrinsically Motivated Learning

Regularity as Intrinsic Reward for Free Play

SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models

Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation

Learning with Muscles

Natural and Robust Walking from Generic Rewards

The effect of muscles in Learning Behavior

Scaling RL to Large Musculoskeletal Systems

Reinforcement Learning for Diverse Solutions

Offline Diversity Under Imitation Constraints

Learning Diverse Skills for Local Navigation

Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations

Reinforcement Learning and Control

Model-based Reinforcement Learning and Planning

Causal Reasoning in RL

Intrinsically Motivated Hierarchical Learner

Regularity as Intrinsic Reward for Free Play

Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation

Natural and Robust Walking from Generic Rewards

Goal-conditioned Offline Planning

Offline Diversity Under Imitation Constraints

Learning Diverse Skills for Local Navigation

Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations

Deep Learning

Combinatorial Optimization as a Layer / Blackbox Differentiation

Symbolic Regression and Equation Learning

Representation Learning

Learning with 3D rotations: A hitchhiker’s guide to SO(3)

ML for Science

Symbolic Regression and Equation Learning

Previous Research Projects

Learning to Control Emulated Muscles in Real Robots: A Software Test Bed for Bio-Inspired Actuators in Hardware

Combinatorial Optimization as a Layer / Blackbox Differentiation

Causal Action Influence Aware Counterfactual Data Augmentation

Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints

Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions

On Imitation in Mean-field Games

Online Learning under Adversarial Nonlinear Constraints

Autonomous Learning

Haptic Sensing

Robots like Poppy need haptic feedback for small-scale (green highlighted fingertip — middle left) and large-scale (white limb — bottom left) surfaces. We aim for creating robust haptic sensors with super-resolution property that reduces taxel number, wiring, and manufacturing costs. Machine learning methods are employed to interpret non-linear raw sensor values into real-world values and timely deliver the host robot needed haptic information, such as contact locations and forces.

The rapid evolution of robotic technologies informs practical benefits in various physical application areas. In complex, changing, and especially human-involved scenarios, a robot must be well-equipped to perceive the interactions between its own body and other things. Due to the visual occlusion and the small scale of the deformations during interactions, robots need touch-sensitive skin in addition to well-developed vision feedback. In this research field, we explore creating durable and robust haptic sensors to meet various application requirements and design machine-learning algorithms to enhance the data processing flow.

Projects

Super-resolution Sensing for Haptics

Introduction Video Haptic feedback is essential to make robots more dexterous and effective in unstructured environments. Nevertheless, high-resolution tactile sensors are still not widely available. When using a large number of physical... Read more

Insight: a Haptic Sensor Powered by Vision and Machine Learning

Introduction Video Robots need detailed haptic sensing that covers their complex surfaces to learn effective behaviors in unstructured environments. However, state-of-the-art sensors tend to focus on improving precision and sensitivity,... Read more

Minsight: Learning-based tactile sensing for robotics

Read more