Hello guest
Your basket is empty
We provide two pathways to the content. Thematic (chapters that address certain themes, e.g. cultivation, regardless of crop or animal type) and Product (chapters that relate to a specific type of crop or animal). Choose the most applicable route to find the right collection for you. 
 
Can’t find what you are looking for? Contact us and let us help you build a custom-made collection. 
You are in: All categories > A-Z Chapters > A
Use the Contact form to discuss the best purchasing method for you... Start building your collection today!

Advances in world modeling for agri-food robotics

Code: 9781835451236
Jordy Senden, Elena Torta and René van de Molengraft, Eindhoven University of Technology, The Netherlands; and Herman Bruyninckx, Eindhoven University of Technology, The Netherlands, Katholieke Universiteit Leuven and Flanders Make, Belgium

Chapter synopsis:

Performing tasks in the agri-food industry can be complex due to the organic, unstructured environments and natural variation in product. Successfully implementing robotic systems in such contexts is highly dependent on their capacity to adapt to variability, unpredictability and incomplete sensor data. Given the multitude of potential unexpected scenarios, it is no longer satisfactory to create fixed plans and controllers for the robot to address a task. Instead, it is essential to model our knowledge of the task and of the robot's operating environment, which is the central concept referred to as a ‘world model’ (WM). In this chapter, we elaborate on the notion of a WM and demonstrate how various WM types can be applied to address tasks in the agri-food domain. In addition to the prevalent geometric world models, we provide an example of the application of a topological WM in an environment devoid of geometric structure. We discuss several topics to improve robustness of task execution, such as multi-modal redundant skills and the use of invariants to describe the world, rather than relying on exact parameters. We argue that robots require an explicit WM as a central component in their software architecture. The software implementation of the WM holds the necessary information about the environment and configuration parameters of the system which are necessary to configure action and detection skills and interpret sensor information. In the future, we argue that these WMs will enable robots to reason online about the situation at hand and on the correct actions to perform to progress the task. The explicit nature of the WM allows robots to share their knowledge, which is crucial when collaborating with humans or other robots.



DOI: 10.19103/AS.2023.0124.02
£25.00
Table of contents
  • 1 Introduction
  • 2 The concept of a world model
  • 3 Invariant-based world models
  • 4 Topological maps with guarded motion
  • 5 Task redundancy through multi-modal sensing
  • 6 Explainable world models for skill configuration
  • 7 Multi-robot cooperation through shared world models
  • 8 Future perspective: world models for reasoning
  • 9 Conclusion
  • 10 Glossary
  • 11 Where to look for further information
  • 12 References

Also in A