{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/interoceptive-robustness-through-environment","title":"Interoceptive robustness through environment-mediated morphological development","arxiv_id":"1804.02257","date":"2018-04-06","proceeding":null,"authors":["Sam Kriegman","Nick Cheney","Francesco Corucci","Josh C. Bongard"],"abstract":"Typically, AI researchers and roboticists try to realize intelligent behavior\nin machines by tuning parameters of a predefined structure (body plan and/or\nneural network architecture) using evolutionary or learning algorithms. Another\nbut not unrelated longstanding property of these systems is their brittleness\nto slight aberrations, as highlighted by the growing deep learning literature\non adversarial examples. Here we show robustness can be achieved by evolving\nthe geometry of soft robots, their control systems, and how their material\nproperties develop in response to one particular interoceptive stimulus\n(engineering stress) during their lifetimes. By doing so we realized robots\nthat were equally fit but more robust to extreme material defects (such as\nmight occur during fabrication or by damage thereafter) than robots that did\nnot develop during their lifetimes, or developed in response to a different\ninteroceptive stimulus (pressure). This suggests that the interplay between\nchanges in the containing systems of agents (body plan and/or neural\narchitecture) at different temporal scales (evolutionary and developmental)\nalong different modalities (geometry, material properties, synaptic weights)\nand in response to different signals (interoceptive and external perception)\nall dictate those agents' abilities to evolve or learn capable and robust\nstrategies.","url_abs":"http://arxiv.org/abs/1804.02257v2","url_pdf":"http://arxiv.org/pdf/1804.02257v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"interoceptive-robustness-through-environment","repo_url":"https://github.com/skriegman/2018-gecco","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}