b'David Meger'

Learning Intuitive Physics with Multimodal Generative Models

Predicting the future interaction of objects when they come into contact...
01/12/2021 ∙ by Sahand Rezaei-Shoshtari, et al. ∙ 14 ∙ share

read it
Intervention Design for Effective Sim2Real Transfer

The goal of this work is to address the recent success of domain randomi...
12/03/2020 ∙ by Melissa Mozifian, et al. ∙ 2 ∙ share

read it
Multimodal dynamics modeling for off-road autonomous vehicles

Dynamics modeling in outdoor and unstructured environments is difficult ...
11/23/2020 ∙ by Jean-François Tremblay, et al. ∙ 0 ∙ share

read it
Seeing Through your Skin: Recognizing Objects with a Novel Visuotactile Sensor

We introduce a new class of vision-based sensor and associated algorithm...
11/18/2020 ∙ by Francois Robert Hogan, et al. ∙ 0 ∙ share

read it
Learning the Latent Space of Robot Dynamics for Cutting Interaction Inference

Utilization of latent space to capture a lower-dimensional representatio...
07/22/2020 ∙ by Sahand Rezaei-Shoshtari, et al. ∙ 0 ∙ share

read it
An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay

Prioritized Experience Replay (PER) is a deep reinforcement learning tec...
07/12/2020 ∙ by Scott Fujimoto, et al. ∙ 0 ∙ share

read it
3D Shape Reconstruction from Vision and Touch

When a toddler is presented a new toy, their instinctual behaviour is to...
07/07/2020 ∙ by Edward J. Smith, et al. ∙ 7 ∙ share

read it
Vision-Based Goal-Conditioned Policies for Underwater Navigation in the Presence of Obstacles

We present Nav2Goal, a data-efficient and end-to-end learning method for...
06/29/2020 ∙ by Travis Manderson, et al. ∙ 0 ∙ share

read it
Learning to Drive Off Road on Smooth Terrain in Unstructured Environments Using an On-Board Camera and Sparse Aerial Images

We present a method for learning to drive on smooth terrain while simult...
04/09/2020 ∙ by Travis Manderson, et al. ∙ 15 ∙ share

read it
Detecting GAN generated errors

Despite an impressive performance from the latest GAN for generating hyp...
12/02/2019 ∙ by Xiru Zhu, et al. ∙ 71 ∙ share

read it
Unifying Variational Inference and PAC-Bayes for Supervised Learning that Scales

Neural Network based controllers hold enormous potential to learn comple...
10/23/2019 ∙ by Sanjay Thakur, et al. ∙ 0 ∙ share

read it
Deep learning for Aerosol Forecasting

Reanalysis datasets combining numerical physics models and limited obser...
10/14/2019 ∙ by Caleb Hoyne, et al. ∙ 0 ∙ share

read it
Cascaded Gaussian Processes for Data-efficient Robot Dynamics Learning

Motivated by the recursive Newton-Euler formulation, we propose a novel ...
10/05/2019 ∙ by Sahand Rezaei-Shoshtari, et al. ∙ 0 ∙ share

read it
Learning Domain Randomization Distributions for Transfer of Locomotion Policies

Domain randomization (DR) is a successful technique for learning robust ...
06/02/2019 ∙ by Melissa Mozifian, et al. ∙ 0 ∙ share

read it
Human Motion Prediction via Pattern Completion in Latent Representation Space

Inspired by ideas in cognitive science, we propose a novel and general a...
04/18/2019 ∙ by Yi Tian Xu, et al. ∙ 0 ∙ share

read it
Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks

Diversity of environments is a key challenge that causes learned robotic...
03/13/2019 ∙ by Sanjay Thakur, et al. ∙ 0 ∙ share

read it
GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects

Mesh models are a promising approach for encoding the structure of 3D ob...
01/31/2019 ∙ by Edward J. Smith, et al. ∙ 18 ∙ share

read it
Off-Policy Deep Reinforcement Learning without Exploration

Reinforcement learning traditionally considers the task of balancing exp...
12/07/2018 ∙ by Scott Fujimoto, et al. ∙ 0 ∙ share

read it
Synthesizing Neural Network Controllers with Probabilistic Model based Reinforcement Learning

We present an algorithm for rapidly learning controllers for robotics sy...
03/06/2018 ∙ by Juan Camilo Gamboa Higuera, et al. ∙ 0 ∙ share

read it
3D Object Super-Resolution

We consider the problem of scaling deep generative shape models to high-...
02/27/2018 ∙ by Edward Smith, et al. ∙ 0 ∙ share

read it
Cost Adaptation for Robust Decentralized Swarm Behaviour

The multi-agent swarm system is a robust paradigm which can drive effici...
09/21/2017 ∙ by Peter Henderson, et al. ∙ 0 ∙ share

read it
Deep Reinforcement Learning that Matters

In recent years, significant progress has been made in solving challengi...
09/19/2017 ∙ by Peter Henderson, et al. ∙ 0 ∙ share

read it
Benchmark Environments for Multitask Learning in Continuous Domains

As demand drives systems to generalize to various domains and problems, ...
08/14/2017 ∙ by Peter Henderson, et al. ∙ 0 ∙ share

read it
Improved Adversarial Systems for 3D Object Generation and Reconstruction

This paper describes a new approach for training generative adversarial ...
07/29/2017 ∙ by Edward Smith, et al. ∙ 0 ∙ share

read it
Semantic Robot Vision Challenge: Current State and Future Directions

The Semantic Robot Vision Competition provided an excellent opportunity ...
08/19/2009 ∙ by Scott Helmer, et al. ∙ 0 ∙ share

read it

David Meger

Featured Co-authors

Jitendra Malik

Joelle Pineau

Doina Precup

Roberto Calandra

Mark Coates

Georgia Gkioxari

Michal Drozdzal

Peter Henderson

Amy Zhang

Gregory Dudek

Adriana Romero

Learning Intuitive Physics with Multimodal Generative Models

Intervention Design for Effective Sim2Real Transfer

Multimodal dynamics modeling for off-road autonomous vehicles

Seeing Through your Skin: Recognizing Objects with a Novel Visuotactile Sensor

Learning the Latent Space of Robot Dynamics for Cutting Interaction Inference

An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay

3D Shape Reconstruction from Vision and Touch

Vision-Based Goal-Conditioned Policies for Underwater Navigation in the Presence of Obstacles

Learning to Drive Off Road on Smooth Terrain in Unstructured Environments Using an On-Board Camera and Sparse Aerial Images

Detecting GAN generated errors

Unifying Variational Inference and PAC-Bayes for Supervised Learning that Scales

Deep learning for Aerosol Forecasting

Cascaded Gaussian Processes for Data-efficient Robot Dynamics Learning

Learning Domain Randomization Distributions for Transfer of Locomotion Policies

Human Motion Prediction via Pattern Completion in Latent Representation Space

Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks

GEOMetrics: Exploiting Geometric Structure for Graph-Encoded Objects

Off-Policy Deep Reinforcement Learning without Exploration

Synthesizing Neural Network Controllers with Probabilistic Model based Reinforcement Learning

3D Object Super-Resolution

Cost Adaptation for Robust Decentralized Swarm Behaviour

Deep Reinforcement Learning that Matters

Benchmark Environments for Multitask Learning in Continuous Domains

Improved Adversarial Systems for 3D Object Generation and Reconstruction

Semantic Robot Vision Challenge: Current State and Future Directions