- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper introduces CoopLight, a vision-language framework for cooperative traffic signal and connected autonomous vehicle control under long-tail traffic scenarios. It first fine-tunes agents on perception and decision-making VQA tasks, then uses GRPO-based multi-agent co-training to improve semantic report accuracy and cooperative action selection. The agents exchange event locations and confidence levels to integrate complementary observations. Experiments on simulated replicas of two real-world intersections show reduced waiting and travel times, with additional evaluations supporting cross-intersection transfer and robustness to adverse visual conditions.
Critical strengths
-
Well-motivated: The paper addresses practically important long-tail traffic events and clearly explains why compact numerical states are insufficient for effective control.
-
The authors evaluate actual waiting and travel times in traffic simulation, providing evidence of control effectiveness beyond perception accuracy.
-
Experiments cover multiple event types, co-occurring events, cross-intersection transfer, and adverse visual conditions, while ablations support the benefits of vehicle control and communication.
-
The framework is well suited to cooperative traffic control, where roadside and vehicle agents provide complementary observations that support informed signal decisions and proactive vehicle maneuvers.
Critical weaknesses
-
The experiments demonstrate the benefits of vehicle control and communication, but do not isolate the contributions of multi-agent co-training, confidence labels, or self-reflection. The necessity of these components remains unclear.
-
Evaluation is limited to simulated environment of two intersections and predefined event categories. Although transfer and visual robustness experiments are included, generalization to diverse real-world traffic conditions remains unverified.
Questions for authors
- Could the authors provide controlled ablations isolating the effects of GRPO-based multi-agent co-training, confidence labels, and self-reflection? In particular, how does the full method compare with agents trained only through supervised fine-tuning while retaining the same communication mechanism?
- Could the authors clarify whether CoopLight generalizes to unseen event types or configurations beyond the predefined training scenarios? Additional evaluation on more intersection layouts or held-out event configurations would help establish the scope of its generalization.
4 comments
Response to Weakness 2 & Question 2
CoopLight reasons about the traffic consequences of observed events, including blocked movements, remaining dischargeable demand, and emergency priority. The phase-to-movement mapping and camera approach directions are specified for each intersection, allowing the agents to interpret new layouts without assuming the same phase indices or driving conventions.
The main experiments already use disjoint training and evaluation routes within each event category and vary event placement and traffic density. Barriers include construction cones and lane restrictions across different approaches and lanes. Six additional co-occurring-event routes evaluate combinations of long-tail events, where CoopLight obtains lower Overall and CAV AWT than CoTV (manuscript Figure 4a). These results concern unseen configurations and combinations of known event categories, rather than completely unconstrained real-world anomalies.
We further hold out one scenario category at a time from task-specific fine-tuning, train on the remaining categories, and evaluate on the held-out category. Entries report Overall AWT / CAV AWT (seconds).
| Held-out type | Intersection | VLMLight (in-domain reference) | CoopLight (held-out type) | CoopLight (in-domain) |
|---|---|---|---|---|
| Jaywalking | CAL | 26.8 / 27.5 | 22.6 / 11.8 | 18.9 / 9.4 |
| Jaywalking | YMT | 28.3 / 28.7 | 23.4 / 13.6 | 19.5 / 10.2 |
| Incident | CAL | 27.1 / 29.7 | 14.8 / 4.9 | 13.3 / 4.2 |
| Incident | YMT | 26.4 / 27.9 | 14.6 / 15.0 | 13.2 / 14.1 |
| Barrier | CAL | 28.9 / 37.3 | 21.9 / 4.3 | 19.6 / 3.6 |
| Barrier | YMT | 30.8 / 36.5 | 25.8 / 13.4 | 23.2 / 12.3 |
Holding out incidents and barriers increases CoopLight's Overall AWT by 10.9% and 11.4%, respectively, relative to its in-domain model; holding out jaywalking yields a larger 19.8% increase. The held-out CoopLight results are also below the in-domain VLMLight reference in all six comparisons, but that comparison is contextual rather than a matched held-out baseline. Here, an event type is unseen during task-specific fine-tuning, not necessarily unknown to the pretrained VLM.
We additionally evaluate two isolated intersections derived from the InTAS Ingolstadt [1] and TAPAS Cologne [2] SUMO urban-mobility scenarios, which provide city-derived road networks and traffic-demand specifications. Long-tail events are introduced on different approaches and lanes, and the policies trained on CAL and YMT are evaluated without fine-tuning on these additional layouts. These tests assess transfer to new junctions, not network-wide coordinated signal control. Entries report Overall AWT / CAV AWT (seconds).
| Intersection | Scenario | Max-Pressure | VLMLight | CoopLight w/o Comm | CoopLight |
|---|---|---|---|---|---|
| Ingolstadt | Jaywalking | 35.2 / 22.8 | 33.9 / 30.2 | 25.8 / 15.9 | 21.7 / 11.8 |
| Ingolstadt | Incident | 30.4 / 24.1 | 31.2 / 31.5 | 18.7 / 9.6 | 15.6 / 7.9 |
| Ingolstadt | Barrier | 36.8 / 25.6 | 34.7 / 37.9 | 28.9 / 10.4 | 23.9 / 9.1 |
| Cologne | Jaywalking | 33.6 / 21.5 | 32.4 / 29.1 | 24.6 / 14.7 | 20.8 / 11.3 |
| Cologne | Incident | 29.1 / 22.8 | 30.3 / 30.8 | 17.9 / 8.8 | 15.1 / 7.4 |
| Cologne | Barrier | 35.4 / 24.7 | 33.8 / 36.2 | 27.6 / 9.7 | 22.8 / 8.6 |
On these additional junctions, CoopLight averages 20.0 s Overall AWT, compared with 32.7 s for VLMLight and 23.9 s without communication, corresponding to reductions of 38.9% and 16.4%, respectively. The results complement the original CAL–YMT transfer and weather/illumination evaluations, but do not establish transfer to arbitrary cities or validated real-world traffic operation. Scaling semantic cooperation across connected intersections and evaluating field-calibrated traffic remain important future directions.
References
[1] S. Lobo, S. Neumeier, E. M. G. Fernandez, and C. Facchi. InTAS—The Ingolstadt Traffic Scenario for SUMO. SUMO Conference Proceedings, 1:73–92, 2020. doi: 10.52825/scp.v1i.102.
[2] S. Uppoor, O. Trullols-Cruces, M. Fiore, and J. M. Barcelo-Ordinas. Generation and Analysis of a Large-Scale Urban Vehicular Mobility Dataset. IEEE Transactions on Mobile Computing, 13(5):1061–1075, 2014. doi: 10.1109/TMC.2013.27.
Thanks for the detailed relpy. The authors have addressed my concern. They added controlled experiments and discuss about the generalization of the method. I will keep my positive socre.
Thank you for your positive feedback. We sincerely appreciate your constructive suggestions, which have helped us strengthen our evaluation and clarify the generalization capabilities of our method. Thank you again for your time and encouragement.
We thank the reviewer for the positive assessment of the long-tail traffic-control setting, the closed-loop evaluation, and the role of complementary TLS and CAV observations. We appreciate the request to isolate the contributions of multi-agent GRPO co-training, communicated confidence, and self-reflection, and to examine generalization beyond the original scenarios and intersection layouts. Below, we provide controlled component ablations and evaluations on held-out event categories, event combinations, and additional junction layouts, while distinguishing simulation-based transfer from real-world validation and network-wide coordination.
Response to Weakness 1 & Question 1
Thank you for this question. The manuscript's Table 1 separates vehicle-side control (CoopLight w/o CAV) from semantic communication (CoopLight w/o Comm). We further ablate multi-agent GRPO co-training, the confidence field in communicated reports, and the self-reflection step. All variants use the same evaluation scenarios, and each table entry reports Overall AWT / CAV AWT in seconds.
With the communication mechanism retained, SFT-only agents achieve mean Overall AWT of 19.90 s, versus 21.57 s for CoopLight w/o Comm and 17.95 s for full CoopLight. Relative to SFT + communication, joint GRPO reduces Overall AWT by 9.8%. Agent-specific SFT (Eq. 1) trains perception and decision making, while cooperative SFT (Eq. 2) teaches receivers to integrate local observations with ground-truth semantic reports. Multi-agent GRPO (Eq. 3) further optimizes report accuracy and action correctness using agents' generated reports in joint rollouts. This comparison identifies the benefit of co-training beyond supervised initialization, while recognizing that GRPO changes both reporting and decision making.
Removing the confidence field from communicated reports, so that messages contain only event type and location, increases Overall AWT by 10.5% compared with full CoopLight. The increase is larger at YMT (11.4%) than CAL (9.5%), consistent with the more frequent occlusions of its narrower approaches. This specifically tests the value of report-level confidence, not the removal of all confidence-aware perception training.
Without self-reflection on the outcome of the previous phase or maneuver, Overall AWT increases by 13.3% on incident and barrier scenarios, versus 3.9% on jaywalking. Persistent disruptions give the controller more opportunities to repeat an ineffective response, whereas pedestrian crossings tend to be transient. Each ablation degrades performance across the evaluated settings, supporting the contribution of these components within the proposed framework.