# Deep Local Trajectory Replanning and Control for Robot Navigation

## TL;DR

This paper introduces a hierarchical navigation system combining traditional global planning with deep local trajectory planning and attention mechanisms, leading to improved robot navigation performance and interpretability.

## Contribution

The paper presents a novel integration of deep learning with hierarchical planning, enhancing robot navigation with interpretable models and attention-based behavior adjustment.

## Key findings

- Outperforms baseline methods in simulation experiments.
- Shows more consistent performance than traditional navigation systems.
- Utilizes attention mechanisms for interpretable motion control.

## Abstract

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.