Abstract
As robots are becoming a more significant part of humans’ daily life, there is a challenge to bridge the gap between robots’ actions and humans’ understanding of what robots are doing and how they make their decisions. We present an approach to local navigation explanation based on Local Interpretable Model-agnostic Explanations (LIME), a popular approach from the Explainable Artificial Intelligence (XAI) community for explaining individual predictions of black-box models. We show how LIME can be applied to a robot’s local path planner. We experimentally evaluate the explanation method’s runtime, quality, and robustness, and discuss implications for the robotic domain.
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
Notes
- 1.
- 2.
- 3.
We used the following SLIC parametrization: n_segments = 10, compactness = 100.0, max_iter = 1000, min_size_factor = 0.01, max_size_factor = 10.
- 4.
All reported runtime experiments run on a Lenovo Thinkpad E14 Gen2 with AMD Ryzen 5 4500U 2.3 GHz and 16 GB of RAM.
References
Lomas, M., Chevalier, R., Cross, E.V., Garrett, R.C., Hoare, J., Kopack, M.: Explaining robot actions. In: Proceedings of the Seventh Annual ACM/IEEE International Conference on Human-Robot Interaction, pp. 187–188 (2012)
Lim, V., Rooksby, M., Cross, E.S.: Social robots on a global stage: establishing a role for culture during human-robot interaction. Int. J. Soc. Robot. 13(6), 1307–1333 (2021)
IEEE. Ethically aligned design, first edition overview – a vision for prioritizing human well-being with autonomous and intelligent systems. In: Technical Report (2019)
Wachter, S., Mittelstadt, B. and Floridi, L.: Transparent, explainable, and accountable AI for robotics. Sci. Robot. 2(6), eaan6080 (2017)
Edmonds, M., et al.: A tale of two explanations: enhancing human trust by explaining robot behavior. Sci. Robot. 4(7), eaay4663 (2019)
Lindner, F.: Towards a formalization of explanations for robots’ actions and beliefs. In: JOWO 2020 Proceedings of the FOIS Workshop Ontologies for Autonomous Robotics (ROBONTICS 2020) (2020)
Karalus, J., Halilovic, A., Lindner, F.: Explanations in, explanations out: human-in-the-loop social navigation learning. In: ICDL Workshop on Human aligned Reinforcement Learning for Autonomous Agents and Robots (2021)
Tolmeijer, S.: Taxonomy of trust-relevant failures and mitigation strategies. In: Proceedings of HRI 2020 (2020)
Ribeiro, M.T., Singh, S. and Guestrin, C.: Why should I trust you?” explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144 (2016)
Miller, T.: Explanation in artificial intelligence: Insights from the social sciences. Artif. Intell. 267, 1–38 (2019)
Rösmann, C., Feiten, W., Wösch, T., Hoffmann, F., Bertram, T.: Trajectory modification considering dynamic constraints of autonomous robots. In: ROBOTIK 2012; 7th German Conference on Robotics, VDE, pp. 1–6 (2012)
Rosenthal, S., Selvaraj, S.P., Veloso, M.M.: Verbalization: narration of autonomous robot experience. In: IJCAI, vol. 16, pp. 862–868 (2016)
Perera, V., Selveraj, S.P., Rosenthal, S., Veloso, M.: Dynamic generation and refinement of robot verbalization. In: 2016 25th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), pp. 212–218 (2016)
Stein, G.: Generating high-quality explanations for navigation in partially-revealed environments. In: Advances in Neural Information Processing Systems, vol. 34 (2021)
He, L., Aouf, N., Song, B.: Explainable deep reinforcement learning for UAV autonomous path planning. Aerospace Sci. Technol. 118, 107052 (2021)
Bautista-Montesano, R., Bustamante-Bello, R., Ramirez-Mendoza, R.A.: Explainable navigation system using fuzzy reinforcement learning. Int. J. Interact. Des. Manuf. (IJIDeM) 14(4), 1411–1428 (2020)
Brandao, M., Coles, A., Magazzeni, D.: Explaining path plan optimality: fast explanation methods for navigation meshes using full and incremental inverse optimization. In: Proceedings of the International Conference on Automated Planning and Scheduling, vol. 31, pp. 56–64 (2021)
Brandao, M., Canal, G., Krivić, S., Magazzeni, D.: Towards providing explanations for robot motion planning. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 3927-3933. IEEE (2021)
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Patt. Anal. Mach. Intell. 34(11), 2274–2282 (2012)
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
Halilovic, A., Lindner, F. (2022). Explaining Local Path Plans Using LIME. In: Müller, A., Brandstötter, M. (eds) Advances in Service and Industrial Robotics. RAAD 2022. Mechanisms and Machine Science, vol 120. Springer, Cham. https://doi.org/10.1007/978-3-031-04870-8_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-04870-8_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-04869-2
Online ISBN: 978-3-031-04870-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)