Deep Local Trajectory Replanning and Control for Robot Navigation
This work addresses navigation challenges for robots in dynamic environments, but it is incremental as it builds on existing hierarchical planning and machine learning approaches.
The paper tackles robot navigation by combining a global planner with a deep local trajectory planner and velocity controller using attention mechanisms, resulting in improved performance over baselines and more consistent execution compared to traditional systems.
We present a navigation system that combines ideas from hierarchical planning and machine learning. The system uses a traditional global planner to compute optimal paths towards a goal, and a deep local trajectory planner and velocity controller to compute motion commands. The latter components of the system adjust the behavior of the robot through attention mechanisms such that it moves towards the goal, avoids obstacles, and respects the space of nearby pedestrians. Both the structure of the proposed deep models and the use of attention mechanisms make the system's execution interpretable. Our simulation experiments suggest that the proposed architecture outperforms baselines that try to map global plan information and sensor data directly to velocity commands. In comparison to a hand-designed traditional navigation system, the proposed approach showed more consistent performance.