MEDIA ANALYTICS
PROJECTS
PEOPLE
PUBLICATIONS
PATENTS
We develop embodied agents for robotics applications that require exploration, navigation and transport in complex scenes. Our modular hierarchical transport policy builds a topological graph of the scene to perform exploration, then combined motion planning algorithms to reach point goals within explored locations with object navigation policies for moving towards semantic targets at unknown locations. Our modular approach for long-horizon transport allows generalization to harder scenes with training only on simpler versions of the task. We also develop new paradigms for deep exploration and long-horizon planning in embodied AI, where the agent is required to efficiently find and transport objects to a goal location, with load constraints and variable capacities.
Team Members: Adarsh Modh, Vijay Kumar BG, Manmohan Chandraker
We aim to address key challenges in long-horizon embodied exploration and navigation by proposing a long-horizon object transport task called Long-HOT and a novel modular framework for temporally extended navigation. Agents in Long-HOT need to efficiently find and pick up target objects that are scattered
