Federico Pigozzi
Eric Medvet
ABSTRACT
A vital component of intelligent action is affordance detection: understanding what actions external objects afford the viewer. This requires the agent to understand the physical nature of the object being viewed, its own physical nature, and the potential relationships possible when they interact. Although robotics researchers have investigated affordance detection, the way in which the morphology of the robot facilitates, obstructs, or otherwise influences the robot's ability to detect affordances has yet to be studied. We do so here and find that a robot with an appropriate morphology can evolve to predict whether it will fit through an aperture with just minimal tactile feedback. We also find that some robot morphologies facilitate the evolution of more accurate affordance detection, while others do not if all have the same evolutionary optimization budget. This work demonstrates that sensation, thought, and action are necessary but not sufficient for understanding how affordance detection may evolve in organisms or robots: morphology must also be taken into account. It also suggests that, in the future, we may optimize morphology along with control in order to facilitate affordance detection in robots, and thus improve their reliable and safe action in the world.
- Randall D Beer et al. 1996. Toward the evolution of dynamical neural networks for minimally cognitive behavior. From animals to animats 4 (1996), 421--429.Google Scholar
- Josh Bongard, Victor Zykov, and Hod Lipson. 2006. Resilient machines through continuous self-modeling. Science 314, 5802 (2006), 1118--1121.Google ScholarCross Ref
- Boyuan Chen, Robert Kwiatkowski, Carl Vondrick, and Hod Lipson. 2022. Fully body visual self-modeling of robot morphologies. Science Robotics 7, 68 (2022).Google Scholar
- Nick Cheney, Josh Bongard, and Hod Lipson. 2015. Evolving soft robots in tight spaces. In Proceedings of the 2015 annual conference on Genetic and Evolutionary Computation. ACM, 935--942.Google ScholarDigital Library
- Francesco Corucci, Nick Cheney, Francesco Giorgio-Serchi, Josh Bongard, and Cecilia Laschi. 2018. Evolving soft locomotion in aquatic and terrestrial environments: effects of material properties and environmental transitions. Soft robotics 5, 4 (2018), 475--495.Google Scholar
- Antoine Cully, Jeff Clune, Danesh Tarapore, and Jean-Baptiste Mouret. 2015. Robots that can adapt like animals. Nature 521, 7553 (2015), 503--507.Google Scholar
- Kenneth A De Jong. 2006. Evolutionary Computation: A Unified Approach. MIT Press.Google ScholarDigital Library
- Kalyanmoy Deb, Amrit Pratap, Sameer Agarwal, and TAMT Meyarivan. 2002. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE transactions on evolutionary computation 6, 2 (2002), 182--197.Google Scholar
- Jeffrey L Elman. 1990. Finding structure in time. Cognitive science 14, 2 (1990), 179--211.Google Scholar
- James J Gibson. 1977. The theory of affordances. Hilldale, USA 1, 2 (1977), 67--82.Google Scholar
- David Ha and Jürgen Schmidhuber. 2018. Recurrent world models facilitate policy evolution. Advances in neural information processing systems 31 (2018).Google Scholar
- M Hale, Edgar Buchanan Berumen, Alan Winfield, Jon Timmis, Emma Hart, Gusz Eiben, Wei Li, and Andy Tyrrell. 2019. The are robot fabricator: How to (re) produce robots that can evolve in the real world. In International Society for Artificial Life: ALIFE2019. York, 95--102.Google Scholar
- Jonathan Hiller and Hod Lipson. 2012. Automatic design and manufacture of soft robots. IEEE Transactions on Robotics 28, 2 (2012), 457--466.Google ScholarDigital Library
- Jonathan Hiller and Hod Lipson. 2014. Dynamic Simulation of Soft Multimaterial 3D-printed Objects. Soft Robotics 1, 1 (2014), 88--101.Google ScholarCross Ref
- Auke Jan Ijspeert. 2008. Central pattern generators for locomotion control in animals and robots: a review. Neural networks 21, 4 (2008), 642--653.Google ScholarDigital Library
- Julian Kiverstein and Matt Sims. 2021. Is free-energy minimisation the mark of the cognitive? Biology & Philosophy 36, 2 (2021), 25.Google ScholarCross Ref
- Alexander S Klyubin, Daniel Polani, and Chrystopher L Nehaniv. 2005. Empowerment: A universal agent-centric measure of control. In 2005 ieee congress on evolutionary computation, Vol. 1. IEEE, 128--135.Google Scholar
- Sam Kriegman, Amir Mohammadi Nasab, Douglas Blackiston, Hannah Steele, Michael Levin, Rebecca Kramer-Bottiglio, and Josh Bongard. 2021. Scale invariant robot behavior with fractals. arXiv preprint arXiv:2103.04876 (2021).Google Scholar
- Sam Kriegman, Amir Mohammadi Nasab, Dylan Shah, Hannah Steele, Gabrielle Branin, Michael Levin, Josh Bongard, and Rebecca Kramer-Bottiglio. 2020. Scalable sim-to-real transfer of soft robot designs. 2020 3rd IEEE International Conference on Soft Robotics, RoboSoft 2020 (may 2020), 359--366. arXiv:1911.10290 Google ScholarCross Ref
- Jakub Limanowski and Felix Blankenburg. 2013. Minimal self-models and the free energy principle. Frontiers in human neuroscience 7 (2013), 547.Google Scholar
- Sida Liu, David Matthews, Sam Kriegman, and Josh Bongard. 2020. Voxcraft-sim, a GPU-accelerated voxel-based physics engine. https://github.com/voxcraft/voxcraft-sim. Google ScholarCross Ref
- Shanliangzi Liu, Dylan S. Shah, and Rebecca Kramer-Bottiglio. 2021. Highly stretchable multilayer electronic circuits using biphasic gallium-indium. Nature Materials (feb 2021), 1--8. Google ScholarCross Ref
- Georg Martius, Ralf Der, and Nihat Ay. 2013. Information driven self-organization of complex robotic behaviors. PloS one 8, 5 (2013), e63400.Google ScholarCross Ref
- Eric Medvet, Alberto Bartoli, Andrea De Lorenzo, and Giulio Fidel. 2020. Evolution of distributed neural controllers for voxel-based soft robots. In Proceedings of the 2020 Genetic and Evolutionary Computation Conference. 112--120.Google ScholarDigital Library
- Eric Medvet, Alberto Bartoli, Federico Pigozzi, and Marco Rochelli. 2021. Biodiversity in evolved voxel-based soft robots. In Proceedings of the Genetic and Evolutionary Computation Conference. 129--137.Google ScholarDigital Library
- Geoff Nitschke and David Howard. 2021. Autofac: The perpetual robot machine. IEEE Transactions on Artificial Intelligence 3, 1 (2021), 2--10.Google ScholarCross Ref
- Pierre-Yves Oudeyer, Frdric Kaplan, and Verena V Hafner. 2007. Intrinsic motivation systems for autonomous mental development. IEEE transactions on evolutionary computation 11, 2 (2007), 265--286.Google ScholarDigital Library
- Rolf Pfeifer and Josh Bongard. 2006. How the body shapes the way we think: a new view of intelligence. MIT press.Google ScholarDigital Library
- Federico Pigozzi, Yujin Tang, Eric Medvet, and David Ha. 2022. Evolving Modular Soft Robots without Explicit Inter-Module Communication Using Local Self-Attention. In Proceedings of the Genetic and Evolutionary Computation Conference. 148--157.Google ScholarDigital Library
- Sebastian Risi and Kenneth O Stanley. 2019. Deep neuroevolution of recurrent and discrete world models. In Proceedings of the Genetic and Evolutionary Computation Conference. 456--462.Google ScholarDigital Library
- Daniela Rus and Michael T Tolley. 2015. Design, fabrication and control of soft robots. Nature 521, 7553 (2015), 467.Google Scholar
- Dylan S Shah, Joshua P Powers, Liana G Tilton, Sam Kriegman, Josh Bongard, and Rebecca Kramer-Bottiglio. 2021. A soft robot that adapts to environments through shape change. Nature Machine Intelligence 3, 1 (2021), 51--59.Google ScholarCross Ref
- Andrew C Slocum, Douglas C Downey, and Randall D Beer. 2000. Further experiments in the evolution of minimally cognitive behavior: From perceiving affordances to selective attention. In From animals to animats 6: Proceedings of the sixth international conference on simulation of adaptive behavior. Citeseer, 430--439.Google Scholar
- Thomas A Stoffregen. 2018. Affordances as properties of the animal-environment system. In How shall affordances be refined? Four perspectives. Routledge, 115--134.Google Scholar
- Felipe Petroski Such, Vashisht Madhavan, Edoardo Conti, Joel Lehman, Kenneth O Stanley, and Jeff Clune. 2017. Deep neuroevolution: Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning. arXiv preprint arXiv:1712.06567 (2017).Google Scholar
- Aimin Zhou, Bo-Yang Qu, Hui Li, Shi-Zheng Zhao, Ponnuthurai Nagaratnam Suganthan, and Qingfu Zhang. 2011. Multiobjective evolutionary algorithms: A survey of the state of the art. Swarm and evolutionary computation 1, 1 (2011), 32--49.Google Scholar
Index Terms
- Morphology Choice Affects the Evolution of Affordance Detection in Robots
Recommendations
One-Shot Object Affordance Detection in the Wild
AbstractAffordance detection refers to identifying the potential action possibilities of objects in an image, which is a crucial ability for robot perception and manipulation. To empower robots with this ability in unseen scenarios, we first study the ...
The impact of jointly evolving robot morphology and control on adaptation rate
GECCO '09: Proceedings of the 11th Annual conference on Genetic and evolutionary computationEmbodied cognition emphasizes that intelligent behavior results from the coupled dynamics between an agent's body, brain and environment. In response to this, several projects have jointly evolved robot morphology and control to realize desired ...
Towards affordance detection for robot manipulation using affordance for parts and parts for affordance
As robots start to interact with their environments, they need to reason about the affordances of objects in those environments. In most cases, affordances can be inferred only from parts of objects, such as the blade of a knife for cutting or the head ...
Comments