Abstract
For automated vehicles (AVs) to navigate safely, they must be able to anticipate and predict the behavior of pedestrians. This is particularly critical in urban driving environments where risks of collisions are high. However, a major challenge is that pedestrian behavior is inherently multimodal in nature, i.e., pedestrians can plausibly take multiple paths. This is because, in large part, pedestrian behaviors are driven by unique intentions and decisions made by each pedestrian walking along a particular sidewalk or crosswalk. As described in this paper, we developed a hybrid automaton model of multimodal pedestrian behavior called Multimodal Hybrid Pedestrian (MHP) . We account for multimodal pedestrian behavior by identifying pedestrian decision-making points and developing decision-making models to predict pedestrian behaviors in a probabilistic hybrid automaton framework. The resulting MHP model is more likely to predict the ground truth trajectory compared to two baseline models—a baseline hybrid automaton model and a constant velocity model. The MHP model is applicable to a wide variety of urban scenarios—midblocks, intersections, one-way, and two-way streets, etc., and the probabilistic predictions from the model can be utilized for AV motion planning.
Highlights
A major operational challenge for automated vehicles (AVs) in urban environments is the safe navigation around other road users, especially pedestrians, who can change their actions instantaneously
In addition to the tracklets formed by the decisions made by the pedestrians, we considered a tracklet with a non-zero probability that does not have a discrete state but always follows constant velocity dynamics, similar to the baseline constant velocity model
EXPERIMENTATION We developed and tested the Multimodal Hybrid Pedestrian (MHP) model on two urban datasets—Automated Vehicle Interaction in Virtual Reality (AVIVR) dataset and Intersection Drone dataset [64]
Summary
A major operational challenge for automated vehicles (AVs) in urban environments is the safe navigation around other road users, especially pedestrians, who can change their actions instantaneously. AVs must be able to accurately predict the future behavior of pedestrians. These predicted pedestrian trajectories, in turn, can be used for AV motion planning to help the AV safely navigate around pedestrians and avoid collisions. This challenge is problematic at unsignalized crosswalks where the right-of-way between the AV and the pedestrian is unclear. Rudenko et al [20] broadly classifies existing methods for predicting pedestrian behaviors and trajectories into (i) physics-based, (ii) pattern-based, and (iii) planning-based methods. The planning-based methods have been able to better predict the long-term behavior of pedestrians than the other two, they require an assumption about pedestrians’ goals
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
