How good is my prediction? Finding a similarity measure for trajectory prediction evaluation

Quehl, Jannik; Hu, Haohao; Taş, Ömer Şahin; Rehder, Eike; Lauer, Martin

doi:10.1109/itsc.2017.8317825

Cited by 28 publications

(26 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can see that the predicted trajectories are very close to the ground truth ones. Metric: We also adopt Mean Euclidean Distance (MED) [27] to quantitatively evaluate the accuracy of the prediction for continuous trajectories. Given the ground truth trajectory ξ ground =[x g,1 , y g,1 , · · ·, x g,L , y g,L ] T and predicted trajectory ξ prediction =[x p,1 , y p,1 , · · ·, x p,L , y p,L ] T of same length L and same sampling time T , the trajectory similarity is calculated as follows:…”

Section: Test Resultsmentioning

confidence: 99%

Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning

Sun

Zhan

Tomizuka

2018

2018 21st International Conference on Intelligent Transportation Systems (ITSC)

119

View full text Add to dashboard Cite

Autonomous vehicles (AVs) are on the road. To safely and efficiently interact with other road participants, AVs have to accurately predict the behavior of surrounding vehicles and plan accordingly. Such prediction should be probabilistic, to address the uncertainties in human behavior. Such prediction should also be interactive, since the distribution over all possible trajectories of the predicted vehicle depends not only on historical information, but also on future plans of other vehicles that interact with it. To achieve such interaction-aware predictions, we propose a probabilistic prediction approach based on hierarchical inverse reinforcement learning (IRL). First, we explicitly consider the hierarchical trajectory-generation process of human drivers involving both discrete and continuous driving decisions. Based on this, the distribution over all future trajectories of the predicted vehicle is formulated as a mixture of distributions partitioned by the discrete decisions. Then we apply IRL hierarchically to learn the distributions from real human demonstrations. A case study for the ramp-merging driving scenario is provided. The quantitative results show that the proposed approach can accurately predict both the discrete driving decisions such as yield or pass as well as the continuous trajectories.

show abstract

Section: Test Resultsmentioning

confidence: 99%

Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning

Sun

Zhan

Tomizuka

2018

2018 21st International Conference on Intelligent Transportation Systems (ITSC)

119

View full text Add to dashboard Cite

show abstract

“…2) Trajectory Prediction Metrics: The following metrics are the commonly used metrics in the literature. A detailed discussion on other trajectory prediction metrics can be found in [67].…”

Section: A Evaluation Metricsmentioning

confidence: 99%

Deep Learning-Based Vehicle Behavior Prediction for Autonomous Driving Applications: A Review

Mozaffari

Al-Jarrah

Dianati

et al. 2022

IEEE Trans. Intell. Transport. Syst.

421

191

View full text Add to dashboard Cite

show abstract

“…In contrast, recurrent neural networks often directly predict a trajectory [47], [48]. Predicted trajectories can be compared using validation metrics [49] or similarity measures [50]. b) Probability distribution: To consider that other traffic participants have infinitely many future behaviors, we can compute a probability distribution, e. g., of kinematic variables using dynamic Bayesian networks [51]- [53].…”

Section: A Related Workmentioning

confidence: 99%

Set-Based Prediction of Traffic Participants Considering Occlusions and Traffic Rules

Koschi

Althoff

2021

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

Provably safe motion planning for automated road vehicles must ensure that planned motions do not result in a collision with other traffic participants. This is a major challenge in autonomous driving, since the future behavior of other traffic participants is not known and since traffic participants are often hidden due to occlusions. In this work, we propose a formal setbased prediction that contains all acceptable future behaviors of both detected and potentially hidden traffic participants. Based on formalized traffic rules and nondeterministic motion models, we perform reachability analysis to predict the set of possible occupancies and velocities of vehicles, pedestrians, and cyclists. Real-world experiments with a test vehicle in various traffic situations demonstrate the applicability and real-time capability of our over-approximative prediction for both online verification and fail-safe trajectory planning. Even in congested, complex traffic scenarios, our forecasting approach enables self-driving vehicles to never cause accidents.

show abstract

How good is my prediction? Finding a similarity measure for trajectory prediction evaluation

Cited by 28 publications

References 12 publications

Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning

Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning

Deep Learning-Based Vehicle Behavior Prediction for Autonomous Driving Applications: A Review

Set-Based Prediction of Traffic Participants Considering Occlusions and Traffic Rules

Contact Info

Product

Resources

About