research
∙
03/14/2023
MeshDiffusion: Score-based Generative 3D Mesh Modeling
We consider the task of generating realistic 3D shapes, which is useful ...
share
research
∙
03/07/2023
One-4-All: Neural Potential Fields for Embodied Navigation
A fundamental task in robotics is to navigate between two locations. In ...
research
∙
02/14/2023
ConceptFusion: Open-set Multimodal 3D Mapping
Building 3D maps of the environment is central to robot navigation, plan...
research
∙
01/12/2023
Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss
An effective framework for learning 3D representations for perception ta...
research
∙
01/06/2023
Multi-Agent Reinforcement Learning for Fast-Timescale Demand Response of Residential Loads
To integrate high amounts of renewable energy resources, electrical powe...
research
∙
11/24/2022
Estimating Regression Predictive Distributions with Sample Networks
Estimating the uncertainty in deep neural network predictions is crucial...
research
∙
11/14/2022
NeurIPS 2022 Competition: Driving SMARTS
Driving SMARTS is a regular competition designed to tackle problems caus...
research
∙
10/11/2022
Robust and Controllable Object-Centric Learning through Energy-based Models
Humans are remarkably good at understanding and reasoning about complex ...
research
∙
07/20/2022
Structural Causal 3D Reconstruction
This paper considers the problem of unsupervised 3D object reconstructio...
research
∙
07/11/2022
TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs
3D scene graphs (3DSGs) are an emerging description; unifying symbolic, ...
research
∙
03/07/2022
Monocular Robot Navigation with Self-Supervised Pretrained Vision Transformers
In this work, we consider the problem of learning a perception model for...
research
∙
01/05/2022
Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation
In model-free deep reinforcement learning (RL) algorithms, using noisy v...
research
∙
10/27/2021
Iterative Teaching by Label Synthesis
In this paper, we consider the problem of iterative machine teaching, wh...
research
∙
10/16/2021
Lifelong Topological Visual Navigation
The ability for a robot to navigate with only the use of vision is appea...
research
∙
09/29/2021
On Assessing the Usefulness of Proxy Domains for Developing and Evaluating Embodied Agents
In many situations it is either impossible or impractical to develop and...
research
∙
09/28/2021
f-Cal: Calibrated aleatoric uncertainty estimation from neural networks for robot perception
While modern deep neural networks are performant perception modules, per...
research
∙
07/09/2021
Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression
Heteroscedastic regression is the task of supervised learning where each...
research
∙
09/09/2020
Integrated Benchmarking and Design for Reproducible and Accessible Evaluation of Robotic Agents
As robotics matures and increases in complexity, it is more necessary th...
research
∙
07/27/2020
La-MAML: Look-ahead Meta Learning for Continual Learning
The continual learning problem involves training models with limited cap...
research
∙
03/12/2020
Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling
We show that the sum of the implicit generator log-density log p_g of a ...
research
∙
02/19/2020
Curriculum in Gradient-Based Meta-Reinforcement Learning
Gradient-based meta-learners such as Model-Agnostic Meta-Learning (MAML)...
research
∙
02/18/2020
Generating Automatic Curricula via Self-Supervised Active Domain Randomization
Goal-directed Reinforcement Learning (RL) traditionally considers an age...
research
∙
10/23/2019
gradSLAM: Dense SLAM meets Automatic Differentiation
The question of "representation" is central in the context of dense simu...
research
∙
06/25/2019
Perceptual Generative Autoencoders
Modern generative models are usually designed to match target distributi...
research
∙
04/09/2019
Active Domain Randomization
Domain randomization is a popular technique for improving domain transfe...
research
∙
03/06/2019
The AI Driving Olympics at NeurIPS 2018
Despite recent breakthroughs, the ability of deep learning and reinforce...
research
∙
03/05/2019
Deep Active Localization
Active localization is the problem of generating robot actions that allo...
research
∙
10/11/2018
A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies
Learning effective visuomotor policies for robots purely from data is ch...
research
∙
04/11/2018