Details
| Original language | English |
|---|---|
| Pages (from-to) | 5-17 |
| Number of pages | 13 |
| Journal | IEEE Transactions on Intelligent Vehicles |
| Volume | 3 |
| Issue number | 1 |
| Publication status | Published - Mar 2018 |
| Externally published | Yes |
Abstract
Automated driving requires decision making in dynamic and uncertain environments. The uncertainty from the prediction originates from the noisy sensor data and from the fact that the intention of human drivers cannot be directly measured. This problem is formulated as a partially observable Markov decision process (POMDP) with the intended route of the other vehicles as hidden variables. The solution of the POMDP is a policy determining the optimal acceleration of the ego vehicle along a preplanned path. Therefore, the policy is optimized for the most likely future scenarios resulting from an interactive, probabilistic motion model for the other vehicles. Considering possible future measurements of the surrounding cars allows the autonomous car to incorporate the estimated change in future prediction accuracy in the optimal policy. A compact representation results in a low-dimensional state-space. Thus, the problem can be solved online for varying road layouts and number of vehicles. This is done with a point-based solver in an anytime fashion on a continuous state-space. Our evaluation is threefold: At first, the convergence of the algorithm is evaluated and it is shown how the convergence can be improved with an additional search heuristic. Second, we show various planning scenarios to demonstrate how the introduction of different considered uncertainties results in more conservative planning. At the end, we show online simulations for the crossing of complex (unsignalized) intersections. We can demonstrate that our approach performs nearly as good as with full prior information about the intentions of the other vehicles and clearly outperforms reactive approaches.
Keywords
- Autonomous driving, decision making, interaction, motion planning under uncertainty, POMDP
ASJC Scopus subject areas
- Computer Science(all)
- Artificial Intelligence
- Engineering(all)
- Automotive Engineering
- Mathematics(all)
- Control and Optimization
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: IEEE Transactions on Intelligent Vehicles, Vol. 3, No. 1, 03.2018, p. 5-17.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Automated Driving in Uncertain Environments
T2 - Planning with Interaction and Uncertain Maneuver Prediction
AU - Hubmann, Constantin
AU - Schulz, Jens
AU - Becker, Marvin
AU - Althoff, Daniel
AU - Stiller, Christoph
N1 - Publisher Copyright: © 2016 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2018/3
Y1 - 2018/3
N2 - Automated driving requires decision making in dynamic and uncertain environments. The uncertainty from the prediction originates from the noisy sensor data and from the fact that the intention of human drivers cannot be directly measured. This problem is formulated as a partially observable Markov decision process (POMDP) with the intended route of the other vehicles as hidden variables. The solution of the POMDP is a policy determining the optimal acceleration of the ego vehicle along a preplanned path. Therefore, the policy is optimized for the most likely future scenarios resulting from an interactive, probabilistic motion model for the other vehicles. Considering possible future measurements of the surrounding cars allows the autonomous car to incorporate the estimated change in future prediction accuracy in the optimal policy. A compact representation results in a low-dimensional state-space. Thus, the problem can be solved online for varying road layouts and number of vehicles. This is done with a point-based solver in an anytime fashion on a continuous state-space. Our evaluation is threefold: At first, the convergence of the algorithm is evaluated and it is shown how the convergence can be improved with an additional search heuristic. Second, we show various planning scenarios to demonstrate how the introduction of different considered uncertainties results in more conservative planning. At the end, we show online simulations for the crossing of complex (unsignalized) intersections. We can demonstrate that our approach performs nearly as good as with full prior information about the intentions of the other vehicles and clearly outperforms reactive approaches.
AB - Automated driving requires decision making in dynamic and uncertain environments. The uncertainty from the prediction originates from the noisy sensor data and from the fact that the intention of human drivers cannot be directly measured. This problem is formulated as a partially observable Markov decision process (POMDP) with the intended route of the other vehicles as hidden variables. The solution of the POMDP is a policy determining the optimal acceleration of the ego vehicle along a preplanned path. Therefore, the policy is optimized for the most likely future scenarios resulting from an interactive, probabilistic motion model for the other vehicles. Considering possible future measurements of the surrounding cars allows the autonomous car to incorporate the estimated change in future prediction accuracy in the optimal policy. A compact representation results in a low-dimensional state-space. Thus, the problem can be solved online for varying road layouts and number of vehicles. This is done with a point-based solver in an anytime fashion on a continuous state-space. Our evaluation is threefold: At first, the convergence of the algorithm is evaluated and it is shown how the convergence can be improved with an additional search heuristic. Second, we show various planning scenarios to demonstrate how the introduction of different considered uncertainties results in more conservative planning. At the end, we show online simulations for the crossing of complex (unsignalized) intersections. We can demonstrate that our approach performs nearly as good as with full prior information about the intentions of the other vehicles and clearly outperforms reactive approaches.
KW - Autonomous driving
KW - decision making
KW - interaction
KW - motion planning under uncertainty
KW - POMDP
UR - http://www.scopus.com/inward/record.url?scp=85060483891&partnerID=8YFLogxK
U2 - 10.1109/tiv.2017.2788208
DO - 10.1109/tiv.2017.2788208
M3 - Article
AN - SCOPUS:85060483891
VL - 3
SP - 5
EP - 17
JO - IEEE Transactions on Intelligent Vehicles
JF - IEEE Transactions on Intelligent Vehicles
IS - 1
ER -