Intention-Aware Pedestrian Avoidance
A critical component of autonomous driving in urban environment is the vehicle’s ability to interact safely and intelligently with the human drivers and on-road pedestrians. This requires identifying the human intentions in real time based on a limited observation history and reacting accordingly. I...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Book |
| Language: | English |
| Published: |
Springer International Publishing
2021
|
| Online Access: | https://hdl.handle.net/1721.1/129707 |
| _version_ | 1826210716277800960 |
|---|---|
| author | Bandyopadhyay, Tirthankar Jie, Chong Zhuang Hsu, David Ang, Marcelo H. Rus, Daniela L Frazzoli, Emilio |
| author2 | Singapore-MIT Alliance in Research and Technology (SMART) |
| author_facet | Singapore-MIT Alliance in Research and Technology (SMART) Bandyopadhyay, Tirthankar Jie, Chong Zhuang Hsu, David Ang, Marcelo H. Rus, Daniela L Frazzoli, Emilio |
| author_sort | Bandyopadhyay, Tirthankar |
| collection | MIT |
| description | A critical component of autonomous driving in urban environment is the vehicle’s ability to interact safely and intelligently with the human drivers and on-road pedestrians. This requires identifying the human intentions in real time based on a limited observation history and reacting accordingly. In the context of pedestrian avoidance, traditional approaches like proximity based reactive avoidance, or taking the most likely behavior of the pedestrian into account, often fail to generate a safe and successful avoidance strategy. This is mainly because they fail to take into account the human intention and the inherent uncertainty resulting in identifying such intentions from direct observations.
This work formulates the on-road pedestrian avoidance problem as an instance of the Intention-Aware Motion Planning (IAMP) problem, where the human intention uncertainty is incorporated in a principled manner into the planning framework. Assuming a set of all possible pedestrian intentions in the environment, IAMPs generate a Mixed Observable Markov Decision Process (MOMDP), (a factored variant of Partially Obervable Markov Decision Process (POMDP)) with the human intentions being the unobserved variables. Solving the resulting MOMDP generates a robust pedestrian avoidance policy. In spite of the criticism of POMDPs to be computationally intractable in general, we show that with proper state factorization and latest sampling based approaches the policy can be executed online on a real vehicle on road. We demonstrate this by running the algorithm on a real pedestrian crossing in the NUS campus successfully handling the intentions for multiple pedestrians, even when they are jaywalking. In this paper, we present results in simulation to show the improved performance of the proposed approach over existing methods. Additionally, we present results validating experimentally the assumptions made in formulating the intention aware pedestrian avoidance problem.
This work presents a preliminary step towards safer and effective autonomous navigation in urban environments by incorporating the intentions of pedestrians and other drivers on the road. |
| first_indexed | 2024-09-23T14:54:02Z |
| format | Book |
| id | mit-1721.1/129707 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T14:54:02Z |
| publishDate | 2021 |
| publisher | Springer International Publishing |
| record_format | dspace |
| spelling | mit-1721.1/1297072022-10-01T23:16:45Z Intention-Aware Pedestrian Avoidance Bandyopadhyay, Tirthankar Jie, Chong Zhuang Hsu, David Ang, Marcelo H. Rus, Daniela L Frazzoli, Emilio Singapore-MIT Alliance in Research and Technology (SMART) Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Laboratory for Information and Decision Systems A critical component of autonomous driving in urban environment is the vehicle’s ability to interact safely and intelligently with the human drivers and on-road pedestrians. This requires identifying the human intentions in real time based on a limited observation history and reacting accordingly. In the context of pedestrian avoidance, traditional approaches like proximity based reactive avoidance, or taking the most likely behavior of the pedestrian into account, often fail to generate a safe and successful avoidance strategy. This is mainly because they fail to take into account the human intention and the inherent uncertainty resulting in identifying such intentions from direct observations. This work formulates the on-road pedestrian avoidance problem as an instance of the Intention-Aware Motion Planning (IAMP) problem, where the human intention uncertainty is incorporated in a principled manner into the planning framework. Assuming a set of all possible pedestrian intentions in the environment, IAMPs generate a Mixed Observable Markov Decision Process (MOMDP), (a factored variant of Partially Obervable Markov Decision Process (POMDP)) with the human intentions being the unobserved variables. Solving the resulting MOMDP generates a robust pedestrian avoidance policy. In spite of the criticism of POMDPs to be computationally intractable in general, we show that with proper state factorization and latest sampling based approaches the policy can be executed online on a real vehicle on road. We demonstrate this by running the algorithm on a real pedestrian crossing in the NUS campus successfully handling the intentions for multiple pedestrians, even when they are jaywalking. In this paper, we present results in simulation to show the improved performance of the proposed approach over existing methods. Additionally, we present results validating experimentally the assumptions made in formulating the intention aware pedestrian avoidance problem. This work presents a preliminary step towards safer and effective autonomous navigation in urban environments by incorporating the intentions of pedestrians and other drivers on the road. 2021-02-08T18:59:19Z 2021-02-08T18:59:19Z 2013 2019-07-16T17:25:19Z Book http://purl.org/eprint/type/ConferencePaper 9783319000640 9783319000657 1610-7438 1610-742X https://hdl.handle.net/1721.1/129707 Bandyopadhyay, Tirthankar et al. "Intention-Aware Pedestrian Avoidance." Experimental Robotics, edited by Jaydev P. Desai et al., Springer International Publishing, 2013, 963-977. © 2013 Springer International Publishing en http://dx.doi.org/10.1007/978-3-319-00065-7_64 Experimental Robotics Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Springer International Publishing MIT web domain |
| spellingShingle | Bandyopadhyay, Tirthankar Jie, Chong Zhuang Hsu, David Ang, Marcelo H. Rus, Daniela L Frazzoli, Emilio Intention-Aware Pedestrian Avoidance |
| title | Intention-Aware Pedestrian Avoidance |
| title_full | Intention-Aware Pedestrian Avoidance |
| title_fullStr | Intention-Aware Pedestrian Avoidance |
| title_full_unstemmed | Intention-Aware Pedestrian Avoidance |
| title_short | Intention-Aware Pedestrian Avoidance |
| title_sort | intention aware pedestrian avoidance |
| url | https://hdl.handle.net/1721.1/129707 |
| work_keys_str_mv | AT bandyopadhyaytirthankar intentionawarepedestrianavoidance AT jiechongzhuang intentionawarepedestrianavoidance AT hsudavid intentionawarepedestrianavoidance AT angmarceloh intentionawarepedestrianavoidance AT rusdanielal intentionawarepedestrianavoidance AT frazzoliemilio intentionawarepedestrianavoidance |