6 papers
Camera-to-Robot Pose Estimation from a Single Image
Timothy E. Lee, Jonathan Tremblay, Thang To +5
We present an approach for estimating the pose of an external camera with respect to a robot using a single RGB image of the robot. The image is processed by a deep neural network…
Toward Sim-to-Real Directional Semantic Grasping
Shariq Iqbal, Jonathan Tremblay, Thang To +6
We address the problem of directional semantic grasping, that is, grasping a specific object from a specific direction. We approach the problem using deep reinforcement learning vi…
Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects
Jonathan Tremblay, Thang To, Balakumar Sundaralingam +3
Using synthetic data for training deep neural networks for robotic manipulation holds the promise of an almost unlimited amount of pre-labeled training data, generated safely out o…
Synthetically Trained Neural Networks for Learning Human-Readable Plans from Real-World Demonstrations
Jonathan Tremblay, Thang To, Artem Molchanov +3
We present a system to infer and execute a human-readable program from a real-world demonstration. The system consists of a series of neural networks to perform perception, program…
Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization
Jonathan Tremblay, Aayush Prakash, David Acuna +7
We present a system for training deep neural networks for object detection using synthetic images. To handle the variability in real-world data, the system relies upon the techniqu…
Falling Things: A Synthetic Dataset for 3D Object Detection and Pose Estimation
Jonathan Tremblay, Thang To, Stan Birchfield
We present a new dataset, called Falling Things (FAT), for advancing the state-of-the-art in object detection and 3D pose estimation in the context of robotics. By synthetically co…