SHIFT Planner: Speedy Hybrid Iterative Field and Segmented Trajectory Optimization with IKD-tree for Uniform Lightweight Coverage

TL;DR

This paper presents SHIFT Planner, a hybrid iterative planning framework that integrates semantic mapping, adaptive coverage, and dynamic obstacle avoidance to optimize robot coverage and trajectory tracking in complex environments.

Contribution

It introduces the Radiant Field-Informed Coverage Planning algorithm, utilizing a diffusion model for dynamic, environment-aware trajectory and speed adjustment.

Findings

Achieves uniform, speed-optimized coverage trajectories.

Effectively adapts to environmental conditions like dirtiness and dryness.

Integrates semantic mapping with trajectory planning.

Abstract

This paper introduces a comprehensive planning and navigation framework that address these limitations by integrating semantic mapping, adaptive coverage planning, dynamic obstacle avoidance and precise trajectory tracking. Our framework begins by generating panoptic occupancy local semantic maps and accurate localization information from data aligned between a monocular camera, IMU, and GPS. This information is combined with input terrain point clouds or preloaded terrain information to initialize the planning process. We propose the Radiant Field-Informed Coverage Planning algorithm, which utilizes a diffusion field model to dynamically adjust the robot's coverage trajectory and speed based on environmental attributes such as dirtiness and dryness. By modeling the spatial influence of the robot's actions using a Gaussian field, ensures a speed-optimized, uniform coverage trajectory while adapting to varying environmental conditions.