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.
hub
Congested traffic states in empirical observations and microscopic simulations
10 Pith papers cite this work, alongside 3,935 external citations. Polarity classification is still indexing.
10
Pith papers citing it
3,935
external citations · Crossref
abstract
We present data from several German freeways showing different kinds of congested traffic forming near road inhomogeneities, specifically lane closings, intersections, or uphill gradients. The states are localized or extended, homogeneous or oscillating. Combined states are observed as well, like the coexistence of moving localized clusters and clusters pinned at road inhomogeneities, or regions of oscillating congested traffic upstream of nearly homogeneous congested traffic. The experimental findings are consistent with a recently proposed theoretical phase diagram for traffic near on-ramps [D. Helbing, A. Hennecke, and M. Treiber, Phys. Rev. Lett. {\bf 82}, 4360 (1999)]. We simulate these situations with a novel continuous microscopic single-lane model, the ``intelligent driver model'' (IDM), using the empirical boundary conditions. All observations, including the coexistence of states, are qualitatively reproduced by describing inhomogeneities with local variations of one model parameter. We show that the results of the microscopic model can be understood by formulating the theoretical phase diagram for bottlenecks in a more general way. In particular, a local drop of the road capacity induced by parameter variations has practically the same effect as an on-ramp.
hub tools
citation-role summary
background 2
method 1
citation-polarity summary
verdicts
UNVERDICTED 10representative citing papers
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.
SCSL enables composing tests from elementary scenarios with online execution and dynamic reconfiguration to handle nondeterminism and changing configurations in distributed robot systems.
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.
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.
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.
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.
Hierarchical CBF and data-driven control system for suppressing traffic congestion in vehicle simulations.
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.
A conditional flow matching model generates realistic safety-critical traffic scenarios by turning nominal scenes into dangerous rollouts using combined simulation and real data.
citing papers explorer
-
Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy
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.
-
Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Driving
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.
-
Scenario-based System Testing for Distributed Robotics Applications
SCSL enables composing tests from elementary scenarios with online execution and dynamic reconfiguration to handle nondeterminism and changing configurations in distributed robot systems.
-
LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios
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.
-
Human-like autonomy emerges from self-play and a pinch of human data
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.
-
NOVA: Symbolic Regression Discovery of Interpretable Car-Following and Lane-Change Models with Driver Heterogeneity
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.
-
Hyperlocal urban NO2 hotspot modeling driven by microscopic traffic data
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.
-
CBF-based Driving Assistance for Traffic Flow Stabilization
Hierarchical CBF and data-driven control system for suppressing traffic congestion in vehicle simulations.
-
Combined Radar and Magnetometer Sensor Network with LoRa-Mediated Awareness for Wildlife-Vehicle Collision Prevention: A Monte Carlo Analysis
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.
-
Conditional Flow-VAE for Safety-Critical Traffic Scenario Generation
A conditional flow matching model generates realistic safety-critical traffic scenarios by turning nominal scenes into dangerous rollouts using combined simulation and real data.