An Ordering Optimization for Fruit-Vegetable in High-Density Environment based on Genetic Algorithm
An Ordering Optimization for Fruit-Vegetable in High-Density Environment based on Genetic Algorithm
This paper presents a robotic harvesting method combining RGB-D fruit localization, genetic algorithm-based harvest ordering, and waypoint-based robot motion. The approach was evaluated in laboratory and field conditions with varying numbers of fruits. Results indicate that a dynamic-waypoint continuous strategy reduced collision events compared to a static-waypoint strategy, though it achieved a slightly higher target-approach success rate.
The study evaluates a genetic algorithm-based harvesting sequence combined with dynamic waypoint planning in unstructured environments, reporting specific collision counts and success rates from field tests that distinguish between static and dynamic strategies.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- Controlled physical settingOpen source S3
Reported numbers
collision events
40
View original evidence
changed with the remaining fruit distribution without changing the GA sequence. In the field evaluation, the dynamic-waypoint continuous strategy produced 40 collision events and a 70.7% target-approach success rate, compared with 55 collision events and 65.3% for the static-waypoint continuous strategy.
Open source S4collision events
55
View original evidence
changed with the remaining fruit distribution without changing the GA sequence. In the field evaluation, the dynamic-waypoint continuous strategy produced 40 collision events and a 70.7% target-approach success rate, compared with 55 collision events and 65.3% for the static-waypoint continuous strategy.
Open source S4
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
vesting sequence, and static or dynamic waypoints define the intermediate robot motion. The method was evaluated in a controlled laboratory testbed and in four-, five-, and six-fruit field conditions. GA solutions were compared with exhaustive enumeration, and both waypoint offsets were examined by parameter sensitivity analysis. Continuous execution reduced unnecessary Home-return motion, while the dynamic waypoint
Open source S3
changed with the remaining fruit distribution without changing the GA sequence. In the field evaluation, the dynamic-waypoint continuous strategy produced 40 collision events and a 70.7% target-approach success rate, compared with 55 collision events and 65.3% for the static-waypoint continuous strategy.
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org