49 citations · 275 across the 31 of their papers we have counts for
33 papers
ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning
Qiao Gu, Alihusein Kuwajerwala, Sacha Morin +13
For robots to perform a wide variety of tasks, they require a 3D representation of the world that is semantically rich, yet compact and efficient for task-driven perception and pla…
MeshDiffusion: Score-based Generative 3D Mesh Modeling
Zhen Liu, Yao Feng, Michael J. Black +3
We consider the task of generating realistic 3D shapes, which is useful for a variety of applications such as automatic scene generation and physical simulation. Compared to other…
One-4-All: Neural Potential Fields for Embodied Navigation
Sacha Morin, Miguel Saavedra-Ruiz, Liam Paull
A fundamental task in robotics is to navigate between two locations. In particular, real-world navigation can require long-horizon planning using high-dimensional RGB images, which…
ConceptFusion: Open-set Multimodal 3D Mapping
Krishna Murthy Jatavallabhula, Alihusein Kuwajerwala, Qiao Gu +14
Building 3D maps of the environment is central to robot navigation, planning, and interaction with objects in a scene. Most existing approaches that integrate semantic concepts wit…
Multi-Agent Reinforcement Learning for Fast-Timescale Demand Response of Residential Loads
Vincent Mai, Philippe Maisonneuve, Tianyu Zhang +3
To integrate high amounts of renewable energy resources, electrical power grids must be able to cope with high amplitude, fast timescale variations in power generation. Frequency r…
Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss
Anas Mahmoud, Jordan S. K. Hu, Tianshu Kuai +3
An effective framework for learning 3D representations for perception tasks is distilling rich self-supervised image features via contrastive learning. However, image-to point repr…
Estimating Regression Predictive Distributions with Sample Networks
Ali Harakeh, Jordan Hu, Naiqing Guan +2
Estimating the uncertainty in deep neural network predictions is crucial for many real-world applications. A common approach to model uncertainty is to choose a parametric distribu…
NeurIPS 2022 Competition: Driving SMARTS
Amir Rasouli, Randy Goebel, Matthew E. Taylor +15
Driving SMARTS is a regular competition designed to tackle problems caused by the distribution shift in dynamic interaction contexts that are prevalent in real-world autonomous dri…
Robust and Controllable Object-Centric Learning through Energy-based Models
Ruixiang Zhang, Tong Che, Boris Ivanovic +4
Humans are remarkably good at understanding and reasoning about complex visual scenes. The capability to decompose low-level observations into discrete objects allows us to build a…
Structural Causal 3D Reconstruction
Weiyang Liu, Zhen Liu, Liam Paull +2
This paper considers the problem of unsupervised 3D object reconstruction from in-the-wild single-view images. Due to ambiguity and intrinsic ill-posedness, this problem is inheren…
TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs
Christopher Agia, Krishna Murthy Jatavallabhula, Mohamed Khodeir +5
3D scene graphs (3DSGs) are an emerging description; unifying symbolic, topological, and metric scene representations. However, typical 3DSGs contain hundreds of objects and symbol…
Monocular Robot Navigation with Self-Supervised Pretrained Vision Transformers
Miguel Saavedra-Ruiz, Sacha Morin, Liam Paull
In this work, we consider the problem of learning a perception model for monocular robot navigation using few annotated images. Using a Vision Transformer (ViT) pretrained with a l…
Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation
Vincent Mai, Kaustubh Mani, Liam Paull
In model-free deep reinforcement learning (RL) algorithms, using noisy value estimates to supervise policy evaluation and optimization is detrimental to the sample efficiency. As t…
On Assessing the Usefulness of Proxy Domains for Developing and Evaluating Embodied Agents
Anthony Courchesne, Andrea Censi, Liam Paull
In many situations it is either impossible or impractical to develop and evaluate agents entirely on the target domain on which they will be deployed. This is particularly true in…
Iterative Teaching by Label Synthesis
Weiyang Liu, Zhen Liu, Hanchen Wang +3
In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner. In contrast to previous…
Lifelong Topological Visual Navigation
Rey Reza Wiyatno, Anqi Xu, Liam Paull
Commonly, learning-based topological navigation approaches produce a local policy while preserving some loose connectivity of the space through a topological map. Nevertheless, spu…
-Cal: Calibrated aleatoric uncertainty estimation from neural networks for robot perception
Dhaivat Bhatt, Kaustubh Mani, Dishank Bansal +3
While modern deep neural networks are performant perception modules, performance (accuracy) alone is insufficient, particularly for safety-critical robotic applications such as sel…
Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression
Vincent Mai, Waleed Khamies, Liam Paull
Heteroscedastic regression is the task of supervised learning where each label is subject to noise from a different distribution. This noise can be caused by the labelling process,…
gradSim: Differentiable simulation for system identification and visuomotor control
Krishna Murthy Jatavallabhula, Miles Macklin, Florian Golemo +11
We consider the problem of estimating an object's physical properties such as mass, friction, and elasticity directly from video sequences. Such a system identification problem is…
Integrated Benchmarking and Design for Reproducible and Accessible Evaluation of Robotic Agents
Jacopo Tani, Andrea F. Daniele, Gianmarco Bernasconi +10
As robotics matures and increases in complexity, it is more necessary than ever that robot autonomy research be reproducible. Compared to other sciences, there are specific challen…
La-MAML: Look-ahead Meta Learning for Continual Learning
Gunshi Gupta, Karmesh Yadav, Liam Paull
The continual learning problem involves training models with limited capacity to perform well on a set of an unknown number of sequentially arriving tasks. While meta-learning show…
Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling
Tong Che, Ruixiang Zhang, Jascha Sohl-Dickstein +4
We show that the sum of the implicit generator log-density of a GAN with the logit score of the discriminator defines an energy function which yields the true data densi…
Curriculum in Gradient-Based Meta-Reinforcement Learning
Bhairav Mehta, Tristan Deleu, Sharath Chandra Raparthy +2
Gradient-based meta-learners such as Model-Agnostic Meta-Learning (MAML) have shown strong few-shot performance in supervised and reinforcement learning settings. However, specific…
Generating Automatic Curricula via Self-Supervised Active Domain Randomization
Sharath Chandra Raparthy, Bhairav Mehta, Florian Golemo +1
Goal-directed Reinforcement Learning (RL) traditionally considers an agent interacting with an environment, prescribing a real-valued reward to an agent proportional to the complet…