{"total":10,"items":[{"citing_arxiv_id":"2606.19370","ref_index":60,"ref_count":1,"confidence":0.88,"is_internal_anchor":true,"paper_title":"Human-like autonomy emerges from self-play and a pinch of human data","primary_cat":"cs.LG","submitted_at":"2026-06-11T19:16:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Self-play RL regularized with 30 minutes of human data produces driving policies that coordinate with humans, training in 15 hours on one GPU with 2500x less data than imitation learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11883","ref_index":12,"ref_count":1,"confidence":0.88,"is_internal_anchor":true,"paper_title":"CBF-based Driving Assistance for Traffic Flow Stabilization","primary_cat":"eess.SY","submitted_at":"2026-06-10T10:10:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Hierarchical CBF and data-driven control system for suppressing traffic congestion in vehicle simulations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.10583","ref_index":13,"ref_count":1,"confidence":0.88,"is_internal_anchor":true,"paper_title":"NOVA: Symbolic Regression Discovery of Interpretable Car-Following and Lane-Change Models with Driver Heterogeneity","primary_cat":"cs.LG","submitted_at":"2026-06-09T08:47:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"NOVA applies symbolic regression to 4.7 million NGSIM observations to identify a two-term car-following model (RMSE 1.376 m/s²) and a lane-change model (67.4% balanced accuracy) that outperform recent baselines and transfer zero-shot between sites.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23117","ref_index":14,"ref_count":1,"confidence":0.88,"is_internal_anchor":true,"paper_title":"Combined Radar and Magnetometer Sensor Network with LoRa-Mediated Awareness for Wildlife-Vehicle Collision Prevention: A Monte Carlo Analysis","primary_cat":"cs.NI","submitted_at":"2026-05-22T00:33:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Monte Carlo simulation of a radar-magnetometer-LoRa sensor network reduces modeled wildlife-vehicle collision rates by 47.4% and increases safe crossings by 77% relative to no mitigation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10034","ref_index":8,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Driving","primary_cat":"cs.RO","submitted_at":"2026-05-11T05:59:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"BehaviorBench reveals that self-play RL policies for autonomous driving overfit to their training traffic agents and do not generalize to other behaviors, motivating a hybrid rule-based plus learned planner.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04366","ref_index":5,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Conditional Flow-VAE for Safety-Critical Traffic Scenario Generation","primary_cat":"cs.RO","submitted_at":"2026-05-06T00:08:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A conditional flow matching model generates realistic safety-critical traffic scenarios by turning nominal scenes into dangerous rollouts using combined simulation and real data.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"and initialization states so that the downstream simulation may yield safety-critical outcomes [3], [4]. In this paper, we focus on generating safety-critical scenarios from a nominal initialization with a roll-out model, where we train a model to directly control the actor maneuvers to be applied upon any nominal initialization. Early approaches rely on manually designed scenarios and heuristic rules [5], often embedded in simulation platforms such as CARLA [6]. These methods offer clear control over vehicle maneuvers by manually specifying the planning trajectory and kinematic constraints. However, they are often limited in scalability and diversity, as each scenario must be explicitly scripted by engineers. The scenario parameters also need to be decided carefully to ensure that there is no"},{"citing_arxiv_id":"2605.03084","ref_index":30,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Hyperlocal urban NO2 hotspot modeling driven by microscopic traffic data","primary_cat":"physics.ao-ph","submitted_at":"2026-05-04T18:59:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Dynamic traffic emissions from an online-calibrated SUMO model improve hyperlocal NO2 hotspot predictions and peak representation over static baselines when coupled to the CAIRDIO dispersion model.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":": Analysis of spatial and temporal patterns of on-road NO x concentrations in Hong Kong. Atmospheric Measurement Techniques11, 6719- 6734 (2018) https://doi.org/10.5194/amt-11-6719-2018 [29] Gipps, P.G.: A behavioural car-following model for computer simulation. Trans- portation Research Part B: Methodological15(2), 105-111 (1981) https://doi. org/10.1016/0191-2615(81)90037-0 [30] Treiber, M., Hennecke, A., Helbing, D.: Congested traffic states in empirical obser- vations and microscopic simulations. Physical Review E62, 1805-1824 (2000) https://doi.org/10.1103/PhysRevE.62.1805 35 [31] Horni, A., Nagel, K., Axhausen, K. (eds.): Multi-Agent Transport Simulation MATSim, p. 618. Ubiquity Press, ??? (2016). https://doi.org/10."},{"citing_arxiv_id":"2604.25772","ref_index":17,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Scenario-based System Testing for Distributed Robotics Applications","primary_cat":"cs.SE","submitted_at":"2026-04-28T15:37:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SCSL enables composing tests from elementary scenarios with online execution and dynamic reconfiguration to handle nondeterminism and changing configurations in distributed robot systems.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Gipps [16] created a mathematical specification formalism for computer-based car-following simulation.Gipps' 42 modelcaptures the behaviour of a single vehicle in a traffic stream, specifi- cally how it reacts to the vehicle in front. The model specifies each braking and acceleration action of the following vehicle. Building on Gipps' work, theIntelligent Driver Model (IDM)[17] introduces time-continuous traffic flow scenario specification with environmental aspects. This enables the sim- ulation of braking manoeuvres or minimum spacing between cars. This was further extended by additional physical simulations of longitudinal dynam- ics, expressed by theOptimal Velocity Model (OVM)[18]. OVM enables the dynamical adjustment of the acceleration after the lead vehicle brakes."},{"citing_arxiv_id":"2505.17209","ref_index":13,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios","primary_cat":"cs.RO","submitted_at":"2025-05-22T18:33:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LiloDriver uses LLMs and memory-augmented planning in a four-stage pipeline to outperform rule-based and learning-based methods on both common and rare scenarios in the nuPlan benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2312.09436","ref_index":57,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy","primary_cat":"cs.RO","submitted_at":"2023-11-27T21:18:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Temporal Transfer Learning selects source tasks for zero-shot transfer of RL policies to solve a range of coarse-grained advisory autonomy hold durations in traffic optimization more reliably than baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}