But most importantly, we are able to implement an exploration policy on a robot which learns to interact with objects completely from scratch just using data collected via the differentiable exploration module.
1 code implementation • 25 Jan 2021 • Anurag Pratik, Soumith Chintala, Kavya Srinet, Dhiraj Gandhi, Rebecca Qian, Yuxuan Sun, Ryan Drew, Sara Elkafrawy, Anoushka Tiwari, Tucker Hart, Mary Williamson, Abhinav Gupta, Arthur Szlam
In recent years, there have been significant advances in building end-to-end Machine Learning (ML) systems that learn at scale.
We use commercially available reacher-grabber assistive tools both as a data collection device and as the robot's end-effector.
We propose a modular system called, `Goal-Oriented Semantic Exploration' which builds an episodic semantic map and uses it to explore the environment efficiently based on the goal object category.
Ranked #4 on Robot Navigation on Habitat 2020 Object Nav test-std
The use of learning provides flexibility with respect to input modalities (in the SLAM module), leverages structural regularities of the world (in global policies), and provides robustness to errors in state estimation (in local policies).
We present an approach to learn an object-centric forward model, and show that this allows us to plan for sequences of actions to achieve distant desired goals.
This paper introduces PyRobot, an open-source robotics framework for research and benchmarking.
The models trained with our home dataset showed a marked improvement of 43. 7% over a baseline model trained with data collected in lab.
Recent self-supervised learning approaches focus on using a few thousand data points to learn policies for high-level, low-dimensional action spaces.
We argue that biological agents use physical interactions with the world to learn visual representations unlike current vision systems which just use passive observations (images and videos downloaded from web).