The Thorvald II Agricultural Robotic System

Grimstad, Lars; From, Pål Johan

doi:10.3390/robotics6040024

Cited by 133 publications

(105 citation statements)

References 9 publications

Supporting

Mentioning

103

Contrasting

Unclassified

Order By: Relevance

“…There is a lot of variation found in agriculture, and there may be large differences between farms, even if they grow the same crop. The mobile platform used in the current work is the Thorvald robot (Grimstad, Skattum, Solberg, Loureiro, & From, ). It is created from modules that may easily be reconfigured into robots of different sizes and shapes for different environments.…”

Section: Related Workmentioning

confidence: 99%

An autonomous strawberry‐harvesting robot: Design, development, integration, and field evaluation

Xiong

Grimstad

et al. 2019

Journal of Field Robotics

Self Cite

289

133

View full text Add to dashboard Cite

This paper presents an autonomous robot capable of picking strawberries continuously in polytunnels. Robotic harvesting in cluttered and unstructured environment remains a challenge. A novel obstacle‐separation algorithm was proposed to enable the harvesting system to pick strawberries that are located in clusters. The algorithm uses the gripper to push aside surrounding leaves, strawberries, and other obstacles. We present the theoretical method to generate pushing paths based on the surrounding obstacles. In addition to manipulation, an improved vision system is more resilient to lighting variations, which was developed based on the modeling of color against light intensity. Further, a low‐cost dual‐arm system was developed with an optimized harvesting sequence that increases its efficiency and minimizes the risk of collision. Improvements were also made to the existing gripper to enable the robot to pick directly into a market punnet, thereby eliminating the need for repacking. During tests on a strawberry farm, the robots first‐attempt success rate for picking partially surrounded or isolated strawberries ranged from 50% to 97.1%, depending on the growth situations. Upon an additional attempt, the pick success rate increased to a range of 75–100%. In the field tests, the system was not able to pick a target that was entirely surrounded by obstacles. This failure was attributed to limitations in the vision system as well as insufficient dexterity in the grippers. However, the picking speed improved upon previous systems, taking just 6.1 s for manipulation operation in the one‐arm mode and 4.6 s in the two‐arm mode.

show abstract

Section: Related Workmentioning

confidence: 99%

An autonomous strawberry‐harvesting robot: Design, development, integration, and field evaluation

Xiong

Grimstad

et al. 2019

Journal of Field Robotics

Self Cite

289

133

View full text Add to dashboard Cite

show abstract

“…In turns, the error between the vertical link position and the monorail system was used to regulate the angular speed of the robots accordingly. Another rail system was proposed in [6], where the authors presented an interesting modular design for a mobile robotic platform. The configuration of this platform was a hybrid approach that allowed the robot to move on a conventional ground mounted rail, while being able to leave the rail of a given row to move to the next one.…”

Section: Related Workmentioning

confidence: 99%

Combining Hector SLAM and Artificial Potential Field for Autonomous Navigation Inside a Greenhouse

Harik

Korsæth

2018

Robotics

View full text Add to dashboard Cite

Abstract:The key factor for autonomous navigation is efficient perception of the surroundings, while being able to move safely from an initial to a final point. We deal in this paper with a wheeled mobile robot working in a GPS-denied environment typical for a greenhouse. The Hector Simultaneous Localization and Mapping (SLAM) approach is used in order to estimate the robots' pose using a LIght Detection And Ranging (LIDAR) sensor. Waypoint following and obstacle avoidance are ensured by means of a new artificial potential field (APF) controller presented in this paper. The combination of the Hector SLAM and the APF controller allows the mobile robot to perform periodic tasks that require autonomous navigation between predefined waypoints. It also provides the mobile robot with a robustness to changing conditions that may occur inside the greenhouse, caused by the dynamic of plant development through the season. In this study, we show that the robot is safe to operate autonomously with a human presence, and that in contrast to classical odometry methods, no calibration is needed for repositioning the robot over repetitive runs. We include here both hardware and software descriptions, as well as simulation and experimental results.

show abstract

“…Mechanical and electrical aspects of the Thorvald II system are described in more detail in Grimstad and From (2017a) and Grimstad and From (2017b). Modules relevant for this paper are described in brief below.…”

Section: Robot Hardwarementioning

confidence: 99%

Software Components of the Thorvald II Modular Robot

Grimstad¹,

From²

2018

MIC

Self Cite

View full text Add to dashboard Cite

In this paper, we present the key software components of the Thorvald II mobile robotic platform. Thorvald II is a modular system developed by the authors for creating robots of arbitrary shapes and sizes, primarily for the agricultural domain. Several robots have been built and are currently operating on farms and universities at various locations in Europe. Robots may take many different forms, and may be configured for differential drive, Ackermann steering, all-wheel drive, all-wheel steering with any number of wheels etc. The software therefore needs to be configuration agnostic. In this paper we present an architecture that allows for simple setup of never-seen-before robot configurations. The presented software is organized in a collection of ROS packages, made available to the reader. These packages allow a user to create her or his own robot configurations and simulate these robots in Gazebo using a provided plugin. Although the presented packages were created to be used with Thorvald robots, they may also be useful for people who are looking to develop their own robot and are interested in testing various robot configurations in simulation before settling on a specific design. To create a robot, the user lists modules with key parameters in one single configuration file and gives this as an input to the robot at startup. Example configuration files are provided within the packages. In this paper, we discuss key aspects of the ROS packages and provide directions on where to find updated information on how to install and use these.

show abstract

The Thorvald II Agricultural Robotic System

Cited by 133 publications

References 9 publications

An autonomous strawberry‐harvesting robot: Design, development, integration, and field evaluation

An autonomous strawberry‐harvesting robot: Design, development, integration, and field evaluation

Combining Hector SLAM and Artificial Potential Field for Autonomous Navigation Inside a Greenhouse

Software Components of the Thorvald II Modular Robot

Contact Info

Product

Resources

About