Learning Diverse Skills for Local Navigation

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

Object-centric Self-supervised Reinforcement Learning

Self-exploration of Behavior

Causal Reasoning in RL

Equation Learner for Extrapolation and Control

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

Object-centric Self-supervised Reinforcement Learning

Symbolic Regression and Equation Learning

Representation Learning

Stepsize adaptation for stochastic optimization

Probabilistic Neural Networks

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

Haptic Sensing

Super-resolution Sensing for Haptics

Insight: a Haptic Sensor Powered by Vision and Machine Learning

Minsight: Learning-based tactile sensing for robotics

ML for Science

Predicting brain activity (fMRI)

Equation Learning for Statistical Physics

Machine Learning for Understanding Quantum Systems

Symbolic Regression and Equation Learning

Previous Research Projects

The Playful Machine

Robust and Affordable Haptic Sensation with Sparse Sensor Configuration

Autonomous Learning Members Website

Learning Diverse Skills for Local Navigation

Dominic — Schematics of our method called DOMiNiC.

We approach the extraction of diverse behaviors in data-driven robot control using a constrained optimization approach to balance quality and diversity through reward-based value function constraints. It shows effective results in a quadruped robot navigation task, with policies that are transferable to real-world scenarios and exhibit agile, diverse behaviors while overcoming obstacles.

Despite many successful applications of data-driven control in robotics, extracting meaningful diverse behaviors remains a challenge. Typically, task performance needs to be compromised in order to achieve diversity. In many scenarios, task requirements are specified as a multitude of reward terms, each requiring a different trade-off. In this work, we take a constrained optimization viewpoint on the quality-diversity trade-off and show that we can obtain diverse policies while imposing constraints on their value functions which are defined through distinct rewards. In line with previous work, further control of the diversity level can be achieved through an attract-repel reward term motivated by the Van der Waals force. We demonstrate the effectiveness of our method on a local navigation task where a quadruped robot needs to reach the target within a finite horizon. Finally, our trained policies transfer well to the real 12-DoF quadruped robot, Solo12, and exhibit diverse agile behaviors with successful obstacle traversal.