Search Results for author:
Found 32 papers, 11 papers with code
Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learning
We introduce PACOH-RL, a novel model-based Meta-Reinforcement Learning (Meta-RL) algorithm designed to efficiently adapt control policies to changing dynamics.
Resilient Legged Local Navigation: Learning to Traverse with Compromised Perception End-to-End
In this paper, we model perception failures as invisible obstacles and pits, and train a reinforcement learning (RL) based local navigation policy to guide our legged robot.
MEM: Multi-Modal Elevation Mapping for Robotics and Learning
Elevation maps are commonly used to represent the environment of mobile robots and are instrumental for locomotion and navigation tasks.
Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning
Instead of relying on a value expectation, we estimate the complete value distribution to account for uncertainty in the robot's interaction with the environment.
Distributional Reinforcement Learning
reinforcement-learning
RAYEN: Imposition of Hard Convex Constraints on Neural Networks
This paper presents RAYEN, a framework to impose hard convex constraints on the output or latent variable of a neural network.
Fast Traversability Estimation for Wild Visual Navigation
We demonstrate the advantages of our approach with experiments and ablation studies in challenging environments in forests, parks, and grasslands.
ORBIT: A Unified Simulation Framework for Interactive Robot Learning Environments
We present ORBIT, a unified and modular framework for robot learning powered by NVIDIA Isaac Sim.
LiDAR-guided object search and detection in Subterranean Environments
Detecting objects of interest, such as human survivors, safety equipment, and structure access points, is critical to any search-and-rescue operation.
Meta Reinforcement Learning for Optimal Design of Legged Robots
We use meta reinforcement learning to train a locomotion policy that can quickly adapt to different designs.
Advanced Skills by Learning Locomotion and Local Navigation End-to-End
It is free to select its path and the locomotion gait.
Self-Supervised Traversability Prediction by Learning to Reconstruct Safe Terrain
Typically, this depends on a semantic understanding which is based on supervised learning from images annotated by a human expert.
Neural Scene Representation for Locomotion on Structured Terrain
We propose a learning-based method to reconstruct the local terrain for locomotion with a mobile robot traversing urban environments.
Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learning
Imitation learning approaches such as adversarial motion priors aim to reduce this problem by encouraging a pre-defined motion style.
Learning-based Localizability Estimation for Robust LiDAR Localization
LiDAR-based localization and mapping is one of the core components in many modern robotic systems due to the direct integration of range and geometry, allowing for precise motion estimation and generation of high quality maps in real-time.
Deep Measurement Updates for Bayes Filters
In this work, we propose the novel approach Deep Measurement Update (DMU) as a general update rule for a wide range of systems.
Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning
In this work, we present and study a training set-up that achieves fast policy generation for real-world robotic tasks by using massive parallelism on a single workstation GPU.
Reconstructing occluded Elevation Information in Terrain Maps with Self-supervised Learning
We first evaluate a supervised learning approach on synthetic data for which we have the full ground-truth available and subsequently move to several real-world datasets.
3D Surfel Map-Aided Visual Relocalization with Learned Descriptors
In this paper, we introduce a method for visual relocalization using the geometric information from a 3D surfel map.
Imitation Learning from MPC for Quadrupedal Multi-Gait Control
We present a learning algorithm for training a single policy that imitates multiple gaits of a walking robot.
Articulated Object Interaction in Unknown Scenes with Whole-Body Mobile Manipulation
A kitchen assistant needs to operate human-scale objects, such as cabinets and ovens, in unmapped environments with dynamic obstacles.
Learning a State Representation and Navigation in Cluttered and Dynamic Environments
We show that decoupling the pipeline into these components results in a sample efficient policy learning stage that can be fully trained in simulation in just a dozen minutes.
Self-supervised Learning of LiDAR Odometry for Robotic Applications
Reliable robot pose estimation is a key building block of many robot autonomy pipelines, with LiDAR localization being an active research domain.
Robotics
Learning Quadrupedal Locomotion over Challenging Terrain
The trained controller has taken two generations of quadrupedal ANYmal robots to a variety of natural environments that are beyond the reach of prior published work in legged locomotion.
A Fully-Integrated Sensing and Control System for High-Accuracy Mobile Robotic Building Construction
We present a fully-integrated sensing and control system which enables mobile manipulator robots to execute building tasks with millimeter-scale accuracy on building construction sites.
Deep Value Model Predictive Control
The DMPC actor is a Model Predictive Control (MPC) optimizer with an objective function defined in terms of a value function estimated by the critic.
DeepGait: Planning and Control of Quadrupedal Gaits using Deep Reinforcement Learning
This paper addresses the problem of legged locomotion in non-flat terrain.
MPC-Net: A First Principles Guided Policy Search
Our loss function, however, corresponds to the minimization of the control Hamiltonian, which derives from the principle of optimality.
Learning agile and dynamic motor skills for legged robots
In the present work, we introduce a method for training a neural network policy in simulation and transferring it to a state-of-the-art legged system, thereby leveraging fast, automated, and cost-effective data generation schemes.
Robust Recovery Controller for a Quadrupedal Robot using Deep Reinforcement Learning
We experimentally validate our approach on the quadrupedal robot ANYmal, which is a dog-sized quadrupedal system with 12 degrees of freedom.
Whole-Body Nonlinear Model Predictive Control Through Contacts for Quadrupeds
In this work we present a whole-body Nonlinear Model Predictive Control approach for Rigid Body Systems subject to contacts.
Robotics
Control of a Quadrotor with Reinforcement Learning
In this paper, we present a method to control a quadrotor with a neural network trained using reinforcement learning techniques.
Robotics
Robust Visual Place Recognition With Graph Kernels
A novel method for visual place recognition is introduced and evaluated, demonstrating robustness to perceptual aliasing and observation noise.
