Impact of jaywalking on pedestrian interaction behavior: A multiagent Markov Game-based analysis
Bibliographic record
Abstract
Jaywalking behavior represents a major safety concern especially in traffic environments with intense pedestrian activity. Despite the influence of this behavior on crash risk given that drivers have unexpected interactions with pedestrians and must take additional evasive actions, limited pedestrian models have accounted for jaywalking behavior. This research uses Multiagent Adversarial Inverse Reinforcement Learning (MAAIRL) within a Markov game framework to model road user behavior in jaywalking scenarios at signalized intersections, offering a detailed representation of the dynamic and complex decision-making strategies of pedestrians and drivers in these situations. This approach enables obtaining reward functions that can be used to make inferences about their behaviors and optimal policies that represent the best sequences of decisions, which can be used in developing microsimulation models. Results show that jaywalking pedestrians exhibited erratic movements, with higher acceleration rates and unpredictable paths. In contrast, non-jaywalking pedestrians showed more predictable behavior with smaller variations in their paths and greater distances from vehicles while crossing. Additionally, jaywalking scenarios led to smaller time-to-collision (TTC) and post-encroachment time (PET) values, reduced minimum distances, and faster pedestrian movements compared to non-jaywalking scenarios, which shows the increased crash risks associated with jaywalking. Finally, the MAAIRL model was able to adequately learn the behaviors associated with both non-jaywalking and jaywalking pedestrians. This shows the potential of this framework to model complex real-world scenarios. These findings underscore the importance of improving pedestrian simulation models to take into account the distinct behavioral patterns associated with jaywalking, and such advancements can facilitate a more comprehensive examination of the safety impacts in busy pedestrian environments.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.002 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".