Energy Efficient Planning for Repetitive Heterogeneous Tasks in Precision Agriculture

2025-04-04

AI Summary

Field robots performing repetitive, heterogeneous weed removal under an “observe-first, act-later” constraint suffer from high energy consumption and redundant mobility. Method: This paper proposes an energy-optimal task planning framework formulated as a mixed-integer nonlinear program (MINLP) that jointly optimizes task reachability and reuse probability. It introduces a task-space partitioning data structure and a region-set covering optimization model, and leverages Renewal Reward theory to model the planning process as a stochastic regenerative system—minimizing long-run average energy consumption. The MINLP is solved efficiently using a Branch-and-Bound solver. Results: Evaluated on real-world farmland data, the method significantly reduces path length, number of stops, total energy consumption, and replanning frequency. It achieves a substantial improvement in energy efficiency, demonstrating a practical breakthrough for sustainable agricultural robotics.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Robotic weed removal in precision agriculture introduces a repetitive heterogeneous task planning (RHTP) challenge for a mobile manipulator. RHTP has two unique characteristics: 1) an observe-first-and-manipulate-later (OFML) temporal constraint that forces a unique ordering of two different tasks for each target and 2) energy savings from efficient task collocation to minimize unnecessary movements. RHTP can be framed as a stochastic renewal process. According to the Renewal Reward Theorem, the expected energy usage per task cycle is the long-run average. Traditional task and motion planning focuses on feasibility rather than optimality due to the unknown object and obstacle position prior to execution. However, the known target/obstacle distribution in precision agriculture allows minimizing the expected energy usage. For each instance in this renewal process, we first compute task space partition, a novel data structure that computes all possibilities of task multiplexing and its probabilities with robot reachability. Then we propose a region-based set-coverage problem to formulate the RHTP as a mixed-integer nonlinear programming. We have implemented and solved RHTP using Branch-and-Bound solver. Compared to a baseline in simulations based on real field data, the results suggest a significant improvement in path length, number of robot stops, overall energy usage, and number of replans.

Problem

• Plan energy-efficient repetitive heterogeneous tasks in agriculture
• Address observe-first-manipulate-later constraints in task planning
• Minimize expected energy usage via stochastic renewal modeling

Innovation

• Stochastic renewal process for energy optimization
• Task space partition for reachability probabilities
• Mixed-integer nonlinear programming for RHTP