Evolution of sustained foraging in 3D environments with physics
Nicolas Chaumont, Christoph Adami

TL;DR
This paper demonstrates the evolution of goal-directed, multi-source foraging behavior in virtual 3D physically realistic environments, highlighting the importance of adaptive strategies and complex controller-body interactions.
Contribution
It introduces a staged evolutionary approach to develop foraging in 3D environments, showing how organisms can learn to reach multiple food sources with high success rates.
Findings
Organisms reached over 90% of food sources on average.
Foraging efficiency depends on previous food source locations.
Evolutionary staging improves foraging capabilities.
Abstract
Artificially evolving foraging behavior in simulated legged animals has proved to be a notoriously difficult task. Here, we co-evolve the morphology and controller for virtual organisms in a three-dimensional physically realistic environment to produce goal-directed legged locomotion. We show that following and reaching multiple food sources can evolve de novo, by evaluating each organism on multiple food sources placed on a basic pattern that is gradually randomized across generations. We devised a strategy of evolutionary "staging", where the best organism from a set of evolutionary experiments using a particular fitness function is used to seed a new set, with a fitness function that is progressively altered to better challenge organisms as evolution improves them. We find that an organism's efficiency at reaching the first food source does not predict its ability at finding…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSpecies Distribution and Climate Change · Robotic Locomotion and Control · Insect and Arachnid Ecology and Behavior
