Search Results for author:
Found 24 papers, 12 papers with code
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.
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.
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.
Lifelong Topological Visual Navigation
However, while end-to-end methods tend to struggle in long-distance navigation tasks, topological map-based solutions are prone to failure due to spurious edges in the graph.
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.
$f$-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.
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.
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.
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).
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.
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.
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.
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.
Orthogonal Over-Parameterized Training
The inductive bias of a neural network is largely determined by the architecture and the training algorithm.
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.
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.
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.
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.
Representation Learning
Simultaneous Localization and Mapping
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.
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.
Deep Active Localization
Traditional approaches to this use an information-theoretic criterion for action selection and hand-crafted perceptual models.
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.
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.
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.
