Abstract
Artificial intelligence is often used in path-planning contexts. Towards improved methods of explainable AI for planned paths, we seek optimally simple explanations to guarantee path safety for a planned route over roads. We present a two-dimensional discrete domain, analogous to a road map, which contains a set of obstacles to be avoided. Given a safe path and constraints on the obstacle locations, we propose a family of specially-defined constraint sets, named explanatory hulls, into which all obstacles may be grouped. We then show that an optimal grouping of the obstacles into such hulls will achieve the absolute minimum number of constraints necessary to guarantee no obstacle-path intersection. From an approximation of this minimal set, we generate a natural-language explanation which communicates path safety in a minimum number of explanatory statements.
This work was supported in part by the United States Department of Defense (DoD) through the National Defense Science and Engineering Graduate (NDSEG) Fellowship Program.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Avoidance rerouter ARR 7000 (2021). https://www.collinsaerospace.com/en/what-we-do/Military-And-Defense/Avionics/Software-Applications/Avoidance-Re-Router-Arr-7000
Boggess, K., Chen, S., Feng, L.: Towards personalized explanation of robot path planning via user feedback. arXiv preprint arXiv:2011.00524 (2020)
Brindise, N.C.: Towards explainable AI: directed inference of linear temporal logic constraints (2021). https://hdl.handle.net/2142/110849
Chakraborti, T., Sreedharan, S., Zhang, Y., Kambhampati, S.: Plan explanations as model reconciliation: moving beyond explanation as soliloquy. In: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI, pp. 156–163 (2017). https://doi.org/10.24963/ijcai.2017/23
Gaglione, J.R., Neider, D., Roy, R., Topcu, U., Xu, Z.: Learning linear temporal properties from noisy data: a maxsat approach. arXiv preprint arXiv:2104.15083 (2021)
Hooker, J.N., et al.: Integrated Methods for Optimization, vol. 170. Springer, NY (2012). https://doi.org/10.1007/978-1-4614-1900-6
Kim, J., Muise, C., Agarwal, S., Agarwal, M.: Bayesltl (2019). https://github.com/IBM/BayesLTL commit 379924d
Kim, J., Muise, C., Shah, A., Agarwal, S., Shah, J.: Bayesian inference of linear temporal logic specifications for contrastive explanations. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, pp. 5591–5598 (2019)
Mittelstadt, B., Russell, C., Wachter, S.: Explaining explanations in AI. In: Proceedings of the Conference on Fairness, Accountability, and Transparency, pp. 279–288 (2019)
Shin, D.: The effects of explainability and causability on perception, trust, and acceptance: implications for explainable AI. Int. J. Hum Comput Stud. 146, 102551 (2021)
Sultana, T., Nemati, H.R.: Impact of explainable AI and task complexity on human-machine symbiosis (2021)
Wells, L., Bednarz, T.: Explainable AI and reinforcement learning–a systematic review of current approaches and trends. Front. Artif. Intell. 4, 48 (2021)
Zhang, W., Lim, B.Y.: Towards relatable explainable AI with the perceptual process. In: CHI Conference on Human Factors in Computing Systems. CHI 2022, Association for Computing Machinery, NY (2022). https://doi.org/10.1145/3491102.3501826
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Brindise, N., Langbort, C. (2022). Communicating Safety of Planned Paths via Optimally-Simple Explanations. In: Bergmann, R., Malburg, L., Rodermund, S.C., Timm, I.J. (eds) KI 2022: Advances in Artificial Intelligence. KI 2022. Lecture Notes in Computer Science(), vol 13404. Springer, Cham. https://doi.org/10.1007/978-3-031-15791-2_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-15791-2_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-15790-5
Online ISBN: 978-3-031-15791-2
eBook Packages: Computer ScienceComputer Science (R0)