• Publications
  • Influence
Learning to Explore using Active Neural SLAM
This work presents a modular and hierarchical approach to learn policies for exploring 3D environments, called `Active Neural SLAM'. Our approach leverages the strengths of both classical andExpand
Learning Exploration Policies for Navigation
TLDR
This work proposes a learning-based approach and finds that the use of policies with spatial memory that are bootstrapped with imitation learning and finally finetuned with coverage rewards derived purely from on-board sensors can be effective at exploring novel environments. Expand
Neural Topological SLAM for Visual Navigation
TLDR
This paper designs topological representations for space that effectively leverage semantics and afford approximate geometric reasoning, and describes supervised learning-based algorithms that can build, maintain and use such representations under noisy actuation. Expand
PyRobot: An Open-source Robotics Framework for Research and Benchmarking
TLDR
PyRobot is a light-weight, high-level interface on top of ROS that provides a consistent set of hardware independent mid-level APIs to control different robots, and will reduce the entry barrier into robotics, and democratize robotics. Expand
BlazingText: Scaling and Accelerating Word2Vec using Multiple GPUs
TLDR
BlazingText is presented, a highly optimized implementation of word2vec in CUDA that can leverage multiple GPUs for training and can achieve a training speed of up to 43M words/sec on 8 GPUs, which is a 9x speedup over 8-threaded CPU implementations, with minimal effect on the quality of the embeddings. Expand
DeepRacer: Educational Autonomous Racing Platform for Experimentation with Sim2Real Reinforcement Learning
TLDR
This work demonstrates how a 1/18th scale car can learn to drive autonomously using RL with a monocular camera and is the first successful large-scale deployment of deep reinforcement learning on a robotic control agent that uses only raw camera images as observations and a model-free learning method to perform robust path planning. Expand
Semantic Visual Navigation by Watching YouTube Videos
TLDR
This paper learns and leverages semantic cues for navigating to objects of interest in novel environments, by simply watching YouTube videos, and improves upon end-to-end RL methods by 66%, while using 250x fewer interactions. Expand
Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Point Clouds
TLDR
A method for automated dataset generation and rapidly generate a training dataset of 50k depth images and 320k object masks synthetically using simulated scenes of 3D CAD models is presented and a variant of Mask R-CNN is trained on the generated dataset to perform category-agnostic instance segmentation without hand-labeled data. Expand
Learning Navigation Subroutines from Egocentric Videos
TLDR
The proposed method to learn hierarchical abstractions, or subroutines from egocentric video data of experts performing tasks, by learning a self-supervised inverse model on small amounts of random interaction data to pseudo-label the expert Egocentric videos with agent actions is demonstrated. Expand
Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects
TLDR
This paper addresses the problem of inferring contact points and the physical forces from videos of humans interacting with objects by using a physics simulator to predict effects, and enforce that estimated forces must lead to same effect as depicted in the video. Expand
...
1
2
3
...