Code for learning a road segmentation network. Duckietown Simulator for data generation with domain randomization: https://github.com/niksaz/randomized-duckietown

The official repository for the paper: Scalable learning for bridging the species gap in image-based plant phenotyping.

Deep reinforcement learning for simultaneous robotic manipulation and locomotion

Sim2Real for joint robotic locomotion and manipulation with RCAN

Using Catalyst.RL to train a robot to perform peg-in-hole insertion in simulation.

A hybrid imitation learning benchmark. Consists of a dataset, metrics and an evaluation approach

Code for simulation to reality (Sim2Real) transfer research for autonomous driving

Sim2RealViz is a visual analytics tool designed to identify the origin of sim2real gaps of Deep Learning models applied to ego-pose localization.

Open simulation tool for large-scale vision-based tactile sensing devices, based on a proposed SOFA-GAZEBO-GAN framework.

CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning

A panoptic segmentation deep learning architecture for sim2real autonomous driving scene understanding

Computational Endoscopy Platform (advanced deep learning toolset for analyzing endoscopy videos) [MICCAI'22, MICCAI'21, ISBI'21, CVPR'20]

Development of an image-based autonomous driving system for an e-FSAE.

Deep Reinforcement Learning for Robotic Grasping from Octrees

Suite of PyBullet reinforcement learning environments targeted towards using tactile data as the main form of observation.

Manager for add-ons in the BenchBot software stack: https://github.com/qcr/benchbot

Evaluation tools for Semantic Scene Understanding with the BenchBot software stack: https://github.com/qcr/benchbot

API for the BenchBot software stack: https://github.com/qcr/benchbot

Supervisor for controlling data flow in the BenchBot software stack: https://github.com/qcr/benchbot