Abstract
The adoption of agent-based modeling represents a transformative approach in the study of spatial cognition, providing a dynamic and flexible framework to explore and enhance navigational behaviors across varied environmental landscapes.
In our study, we crafted and analyzed two specialized agent-based models, each designed for a unique set of conditions: one focuses on navigation in a static environment, while the other is geared towards adaptation in a dynamic setting, both employing mobile agents. Our comparative analysis reveals that agents trained in dynamic settings adapt better when tested in static environments, showing enhanced performance. This improvement highlights the robust adaptability of agents to varied contexts, especially when transitioning from complex, changing environments to simpler, static ones.
However, agents trained in static environments struggle to achieve similar gains in dynamic settings, indicating a challenge in adapting to increased complexity. This asymmetry underscores the importance of dynamic training for developing versatile and effective navigational strategies.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Adami, C., Ofria, C., Collier, T.C.: Evolution of biological complexity. Proc. Natl. Acad. Sci. 97(9), 4463–4468 (2000)
Alonso-Mora, J., DeCastro, J.A., Raman, V., Rus, D., Kress-Gazit, H.: Reactive mission and motion planning with deadlock resolution avoiding dynamic obstacles. Auton. Robot. 42, 801–824 (2018)
Bradbury, J., et al.: JAX: composable transformations of Python+NumPy programs (2018). http://github.com/google/jax
Dhakan, P., Merrick, K., Rañó, I., Siddique, N.: Intrinsic rewards for maintenance, approach, avoidance, and achievement goal types. Front. Neurorobotics 12, 63 (2018)
Durán, J.M.: What is a simulation model? Mind. Mach. 30(3), 301–323 (2020)
Lange, R., et al.: Discovering attention-based genetic algorithms via meta-black-box optimization. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 929–937 (2023)
Maes, P.: Situated agents can have goals. Robot. Auton. Syst. 6(1–2), 49–70 (1990)
Ponticorvo, M., Coccorese, M., Gigliotta, O., Bartolomeo, P., Marocco, D.: Artificial intelligence applied to spatial cognition assessment. In: Ferrández Vicente, J.M., Álvarez-Sánchez, J.R., de la Paz López, F., Adeli, H. (eds.) Artificial Intelligence in Neuroscience: Affective Analysis and Health Applications. IWINAC 2022. LNCS, vol. 13258. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-06242-1_40
Ponticorvo, M., Miglino, O.: Encoding geometric and non-geometric information: a study with evolved agents. Anim. Cogn. 13, 157–174 (2010)
Ponticorvo, M., Walker, R., Miglino, O.: Evolutionary robotics as a tool to investigate spatial cognition in artificial and natural systems. In Artificial Cognition Systems, pp. 210–237. IGI Global (2007)
Ponticorvo, M., Miglino, O.: IS LANGUAGE NECESSARY TO MERGE GEOMETRIC AND NON-GEOMETRIC SPATIAL CUES? THE CASE OF THE “BLUE-WALL TASK”. In: Modeling Language, Cognition And Action, pp. 209-213 (2005)
Roberts, N., Anderson, D., Deal, R., Garet, M., Shaffer, W.: Introduction to computer simulation-a system dynamics modeling approach. J. Oper. Res. Soc. 48(11), 1145–1145 (1997)
Shook, E., Wang, S.: Investigating the influence of spatial and temporal granularities on agent-based modeling. Geogr. Anal. 47(4), 321–348 (2015)
Schillaci, G., Hafner, V.V., Lara, B.: Exploration behaviors, body representations, and simulation processes for the development of cognition in artificial agents. Front. Robot. AI 3, 39 (2016)
Sehnke, F., et al.: Parameter-exploring policy gradients. Neural Netw. 23(4), 551–559 (2010)
Tang, Y., Tian, Y., Ha, D.: EvoJAX: hardware-accelerated neuroevolution. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, pp. 308–311 (2022)
Toklu,N.H., et al.: ClipUp: a simple and powerful optimizer for distribution-based policy evolution. In: International Conference on Parallel Problem Solving from Nature, pp. 515–527 (2020)
Karpathy, A.: REINFORCEjs (2015). https://cs.stanford.edu/people/karpathy/reinforcejs/waterworld.html
Kern, F.: Using the multi-level perspective on socio-technical transitions to assess innovation policy. Technol. Forecast. Soc. Chang. 79(2), 298–310 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Luongo, M., Ponticorvo, M., Milano, N. (2024). Exploring Spatial Cognition: Comparative Analysis of Agent-Based Models in Dynamic and Static Environments. In: Ferrández Vicente, J.M., Val Calvo, M., Adeli, H. (eds) Artificial Intelligence for Neuroscience and Emotional Systems. IWINAC 2024. Lecture Notes in Computer Science, vol 14674. Springer, Cham. https://doi.org/10.1007/978-3-031-61140-7_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-61140-7_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-61139-1
Online ISBN: 978-3-031-61140-7
eBook Packages: Computer ScienceComputer Science (R0)