Achieving uniform coverage in dynamic environments is essential for autonomous robots tasked with cleaning, inspection, and agricultural operations. However, existing approaches often prioritize path length and time optimality, neglecting environmental attributes such as terrain, dirtiness, dryness, and varying elevations in coverage trajectory planning. To address this limitation, we propose the SHIFT Planner framework, which integrates semantic mapping, adaptive coverage planning, and real-time obstacle avoidance to enable comprehensive coverage across diverse terrains and semantic attributes. Key innovations include:
- Radiant Field-Informed Coverage Planning (RFICP) algorithm: Generates trajectories that adapt to terrain variations by aligning with environmental changes. Additionally, a Gaussian diffusion field is employed to ensure efficient and uniform coverage under varying environmental conditions influenced by target semantic attributes.
- Incremental IKD-tree Sliding Window Optimization (IKD-SWOpt): Optimizes trajectory segments within and outside waypoint safety zones by evaluating and refining non-compliant segments through an adaptive sliding window approach. This method not only reduces computational overhead but also guarantees the quality of real-time obstacle avoidance trajectories.