Search Results for author:
Found 39 papers, 15 papers with code
La-MAML: Look-ahead Meta Learning for Continual Learning
The continual learning problem involves training models with limited capacity to perform well on a set of an unknown number of sequentially arriving tasks.
Look-ahead Meta Learning for Continual Learning
The continual learning problem involves training models with limited capacity to perform well on a set of an unknown number of sequentially arriving tasks.
gradSLAM: Automagically differentiable SLAM
Blending representation learning approaches with simultaneous localization and mapping (SLAM) systems is an open question, because of their highly modular and complex nature.
MeshDiffusion: Score-based Generative 3D Mesh Modeling
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.
ConceptFusion: Open-set Multimodal 3D Mapping
ConceptFusion leverages the open-set capabilities of today's foundation models pre-trained on internet-scale data to reason about concepts across modalities such as natural language, images, and audio.
Active Domain Randomization
Our experiments show that domain randomization may lead to suboptimal, high-variance policies, which we attribute to the uniform sampling of environment parameters.
SLAM with Objects using a Nonparametric Pose Graph
The \textit{data association} and \textit{simultaneous localization and mapping} (SLAM) problems are, individually, well-studied in the literature.
On Assessing the Usefulness of Proxy Domains for Developing and Evaluating Embodied Agents
We propose the relative predictive PU to assess the predictive ability of a proxy domain and the learning PU to quantify the usefulness of a proxy as a tool to generate learning data.
Deep Active Localization
Traditional approaches to this use an information-theoretic criterion for action selection and hand-crafted perceptual models.
Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation
In model-free deep reinforcement learning (RL) algorithms, using noisy value estimates to supervise policy evaluation and optimization is detrimental to the sample efficiency.
Perceptual Generative Autoencoders
We therefore propose to map both the generated and target distributions to a latent space using the encoder of a standard autoencoder, and train the generator (or decoder) to match the target distribution in the latent space.
Orthogonal Over-Parameterized Training
The inductive bias of a neural network is largely determined by the architecture and the training algorithm.
TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs
3D scene graphs (3DSGs) are an emerging description; unifying symbolic, topological, and metric scene representations.
Generating Automatic Curricula via Self-Supervised Active Domain Randomization
Goal-directed Reinforcement Learning (RL) traditionally considers an agent interacting with an environment, prescribing a real-valued reward to an agent proportional to the completion of some goal.
Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling
To make that practical, we show that sampling from this modified density can be achieved by sampling in latent space according to an energy-based model induced by the sum of the latent prior log-density and the discriminator output score.
Geometric Consistency for Self-Supervised End-to-End Visual Odometry
We show that using a noisy teacher, which could be a standard VO pipeline, and by designing a loss term that enforces geometric consistency of the trajectory, we can train accurate deep models for VO that do not require ground-truth labels.
A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies
Learning effective visuomotor policies for robots purely from data is challenging, but also appealing since a learning-based system should not require manual tuning or calibration.
Curriculum in Gradient-Based Meta-Reinforcement Learning
However, specifically in the case of meta-reinforcement learning (meta-RL), we can show that gradient-based meta-learners are sensitive to task distributions.
Integrated Benchmarking and Design for Reproducible and Accessible Evaluation of Robotic Agents
As robotics matures and increases in complexity, it is more necessary than ever that robot autonomy research be reproducible.
Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression using Privileged Information
In this work, we consider this setting and additionally assume that the label generating process is able to provide us with a quantity for the role of each label in the misalignment between the datasets, which we consider to be privileged information.
gradSim: Differentiable simulation for system identification and visuomotor control
We consider the problem of estimating an object's physical properties such as mass, friction, and elasticity directly from video sequences.
Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression
In many situations however, the labelling process is able to estimate the variance of such distribution for each label, which can be used as an additional information to mitigate this impact.
$f$-Cal: Calibrated aleatoric uncertainty estimation from neural networks for robot perception
While modern deep neural networks are performant perception modules, performance (accuracy) alone is insufficient, particularly for safety-critical robotic applications such as self-driving vehicles.
Lifelong Topological Visual Navigation
Commonly, learning-based topological navigation approaches produce a local policy while preserving some loose connectivity of the space through a topological map.
Iterative Teaching by Label Synthesis
In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner.
LOCO: Adaptive exploration in reinforcement learning via local estimation of contraction coefficients
We offer a novel approach to balance exploration and exploitation in reinforcement learning (RL).
Monocular Robot Navigation with Self-Supervised Pretrained Vision Transformers
In this work, we consider the problem of learning a perception model for monocular robot navigation using few annotated images.
Structural Causal 3D Reconstruction
This paper considers the problem of unsupervised 3D object reconstruction from in-the-wild single-view images.
Robust and Controllable Object-Centric Learning through Energy-based Models
Humans are remarkably good at understanding and reasoning about complex visual scenes.
NeurIPS 2022 Competition: Driving SMARTS
The proposed competition supports methodologically diverse solutions, such as reinforcement learning (RL) and offline learning methods, trained on a combination of naturalistic AD data and open-source simulation platform SMARTS.
Estimating Regression Predictive Distributions with Sample Networks
A common approach to model uncertainty is to choose a parametric distribution and fit the data to it using maximum likelihood estimation.
Multi-Agent Reinforcement Learning for Fast-Timescale Demand Response of Residential Loads
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.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss
However, image-to point representation learning for autonomous driving datasets faces two main challenges: 1) the abundance of self-similarity, which results in the contrastive losses pushing away semantically similar point and image regions and thus disturbing the local semantic structure of the learned representations, and 2) severe class imbalance as pretraining gets dominated by over-represented classes.
One-4-All: Neural Potential Fields for Embodied Navigation
A fundamental task in robotics is to navigate between two locations.
ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning
We demonstrate the utility of this representation through a number of downstream planning tasks that are specified through abstract (language) prompts and require complex reasoning over spatial and semantic concepts.
Ghost on the Shell: An Expressive Representation of General 3D Shapes
Recent work has focused on the former, and methods for reconstructing open surfaces do not support fast reconstruction with material and lighting or unconditional generative modelling.
GROOD: GRadient-aware Out-Of-Distribution detection in interpolated manifolds
To build this space, GROOD relies on class prototypes together with a prototype that specifically captures OOD characteristics.
CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning
With this dataset, we train a return-conditioned multi-agent behaviour model that allows for fine-grained manipulation of agent behaviours by modifying the desired returns for the various reward components.
Rethinking Teacher-Student Curriculum Learning through the Cooperative Mechanics of Experience
Teacher-Student Curriculum Learning (TSCL) is a curriculum learning framework that draws inspiration from human cultural transmission and learning.
