This paper presents the development, testing and validation of SWEEPER, a robot for harvesting sweet pepper fruit in greenhouses. The robotic system includes a six degrees of freedom industrial arm equipped with a specially designed end effector, RGB-D camera, high-end computer with graphics processing unit, programmable logic controllers, other electronic equipment, and a small container to store harvested fruit. All is mounted on a cart that autonomously drives on pipe rails and concrete floor in the end-user environment. The overall operation of the harvesting robot is described along with details of the algorithms for fruit detection and localization, grasp pose estimation, and motion control. The main contributions of this paper are the integrated system design and its validation and extensive field testing in a commercial greenhouse for different varieties and growing conditions. A total of 262 fruits were involved in a 4-week long testing period. The average cycle time to harvest a fruit was 24 s. Logistics took approximately 50% of this time (7.8 s for discharge of fruit and 4.7 s for platform movements). Laboratory experiments have proven that the cycle time can be reduced to 15 s by running the robot manipulator at a higher speed. The harvest success rates were 61% for the best fit crop conditions and 18% in current crop conditions. This reveals the importance of finding the best fit crop conditions and crop varieties for successful robotic harvesting. The SWEEPER robot is the first sweet pepper harvesting robot to demonstrate this kind of performance in a commercial greenhouse.
A number of algorithms for path tracking are described in the robotics literature. Traditional algorithms, like Pure Pursuit and Follow the Carrot, use position information to compute steering commands that make a vehicle follow a predefined path approximately. These algorithms are well known to cut corners, since they do not explicitly take into account the actual curvature of the path. In this paper we present a novel algorithm that uses recorded steering commands to overcome this problem. The algorithm is constructed within the behavioral paradigm common in intelligent robotics, and is divided into three separate behaviors, each responsible for one aspect of the path tracking task. The algorithm is implemented both on a simulator for autonomous forest machines and a physical small-scale robot. The results are compared with the Pure Pursuit and the Follow the Carrot algorithms, and show a significant improvement in performance.
Accurate vehicle localization in forest environments is still an unresolved problem. Global navigation satellite systems (GNSS) have well known limitations in dense forest, and have to be combined with for instance laser based SLAM algorithms to provide satisfying accuracy. Such algorithms typically require accurate detection of trees, and estimation of tree center locations in laser data. Both these operations depend on accurate estimations of tree trunk diameter. Diameter estimations are important also for several other forestry automation and remote sensing applications. This paper evaluates several existing algorithms for diameter estimation using 2D laser scanner data. Enhanced algorithms, compensating for beam width and using multiple scans, were also developed and evaluated. The best existing algorithms overestimated tree trunk diameter by ca. 40%. Our enhanced algorithms, compensating for laser beam width, reduced this error to less than 12%.
Autonomous navigation in forest terrain, where operation paths are rarely straight or flat and obstacles are common, is challenging. This paper evaluates a system designed to autonomously follow previously demonstrated paths in a forest environment without loading/unloading timber, a pre-step in the development of fully autonomous forwarders. The system consisted of a forwarder equipped with a high-precision global positioning system to measure the vehicle's heading and position. A gyro was used to compensate for the influence of the vehicle's roll and pitch. On an ordinary clear-cut forest area with numerous stumps, the vehicle was able to follow two different tracks, three times each at a speed of 1 m s -1 , with a mean path tracking error of 6 and 7 cm, respectively. The error never exceeded 35 cm, and in 90% of the observations it was less than 14 and 15 cm, respectively. This accuracy is well within the necessary tolerance for forestry operations. In fact, a human operator would probably have a hard time following the track more accurately. Hence, the developed systems function satisfactorily when using previously demonstrated paths. However, further research on planning new paths in unknown unstructured terrain and on loading/unloading is required before timber transports can be fully automated.
In conventional mechanized cut-to-length systems a harvester fells and cuts trees into logs that are stored on the ground until a forwarder picks them up and carries them to landing sites. A proposed improvement is to place logs directly into the load spaces of transporting machines as they are cut. Such integrated loading could result in cost reductions, shorter lead times from stump to landing, and lower fuel consumption. However, it might also create waiting times for the machines involved, whereas multifunctional machines are likely to be expensive. Thus, it is important to analyze whether or not the advantages of any changes outweigh the disadvantages. The conventional system was compared with four potential systems, including two with autonomous forwarders, using discrete-event simulation with stochastic elements in which harvests of more than 1000 nal felling stands (containing in total 1.6 million m 3 ) were simulated 35 times per system. The results indicate that harwarders have substantial potential (less expensive on ≥80% of the volume and fuel consumption decreased by ≥18%) and may become competitive if key innovations are developed. Systems with cooperating machines have considerably less potential, limited to very specic stand conditions. The results conform with expected diculties in integrating processing and transporting machines' work in variable environments.2
Purpose-The purpose of this paper is to describe a generic software framework for development of agricultural and forestry robots. The primary goal is to provide generic high-level functionality and to encourage distributed and structured programming, thus leading to faster and simplified development of robots. A secondary goal is to investigate the value of several architecture views when describing different software aspects of a robotics system. Design/methodology/approach-The framework is constructed with a hybrid robot architecture, with a static state machine that implements a flow diagram describing each specific robot. Furthermore, generic modules for GUI, resource management, performance monitoring, and error handling are included. The framework is described with logical, development, process, and physical architecture views. Findings-The multiple architecture views provide complementary information that is valuable both during and after the design phase. The framework has been shown to be efficient and time saving when integrating work by several partners in several robotics projects. Although the framework is guided by the specific needs of harvesting agricultural robots, the result is believed to be of general value for development also of other types of robots. Originality/value-In this paper, the authors present a novel generic framework for development of agricultural and forestry robots. The robot architecture uses a state machine as replacement for the planner commonly found in other hybrid architectures. The framework is described with multiple architecture views.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.