Minimum‐time row transition control of a vision‐guided agricultural robot

Abstract

This paper presents a vision‐based, subspace optimal controller aiming to improve the row transition performance of an agricultural robot in a strawberry field. The contribution of this paper is twofold. First, only RGB cameras, instead of complicated sensor suites, are used for cross‐bed navigation and row alignment. Second, a real‐time adaptive dynamic programming‐based algorithm is designed for an optimal row transition. The conditions for row alignment are derived in an augmented pixel coordinate frame. Based on these conditions, a simple motion rule is utilized to reduce the search space dimension so that the proposed algorithm can be implemented in real‐time. Additionally, the inverse‐dynamics policy of the algorithm is updated using vision feedback at each control step to adapt to uncertainties. The proposed controller is tested in both simulations and field experiments. In a simulation comparison, the minimum‐time solution achieved using the proposed algorithm is 44.7 s, which is very close to that of a benchmark algorithm (44.4 s). However, the CPU time required by the proposed algorithm is only 4.3% of time needed by the benchmark algorithm. Twenty field experiments using the presented design were all successful in row transition, with a mean final alignment error of 0.5 cm.

Path Planning of Agricultural Information Collection Robot Integrating Ant Colony Algorithm and Particle Swarm Algorithm

“…In formula (1), c represents the learning factor, which can be adjusted to control the flight step size of the particle. k id p represents the optimal individual value reached by the particle during the optimisation process.…”

“…With the development of modern precision agriculture, the efficiency and accuracy of agricultural information collection directly affect the growth management of crops and the operational decision-making of the whole farm. With the advancement of technology, agricultural information collection robots, as an important technological means, are increasingly introduced into this process to improve the automation and intelligence level of data collection [1]. However, these robots are often faced with the variability of agricultural environments when performing tasks, such as uneven vegetation distribution, terrain undulations, and static and dynamic obstacles, which pose significant challenges to path planning [2][3].…”

Expected position and attitude adjustment control method of coal mine roadway support robot

“…The fuzzy PID (Proportional, Integral and Derivative) algorithm based on the optimal deviation path can realize the optimal adjustment control of a wheeled robot (Jin et al, 2020; Luo et al, 2017). A vision‐based subspace optimal controller was proposed for vision‐guided wheeled agricultural robots to improve the position adjustment performance during row transitions (Li & Xu, 2021).…”