sumo
PulseAugur coverage of sumo — every cluster mentioning sumo across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
New research revisits action factorization for complex RL spaces · 2 sources tracked
A new research paper explores methods for handling complex action spaces in reinforcement learning, particularly those that combine discrete and continuous actions. The study analyzes various factorization techniques ac…
-
New generative model Enactor improves traffic intersection simulation
Researchers have developed Enactor, a novel generative model designed for closed-loop microsimulation of signalized intersections. Unlike traditional simulators that use hand-crafted models, Enactor employs an actor-cen…
-
New framework verifies safety of learned multi-agent communication policies
Researchers have developed a novel framework for formally verifying the safety of learned communication policies in multi-agent reinforcement learning (MARL) systems. This approach distills complex neural policies into …
-
Active Inference Controller Optimizes Traffic Signals in Challenging Environments
Researchers have developed an active inference controller for traffic signal management in noisy and unpredictable IoT environments. This controller dynamically selects signal phases by minimizing expected free energy, …
-
New mesoscopic traffic model improves SUMO congestion simulation
Researchers have identified limitations in the mesoscopic traffic flow model used by the Simulation of Urban MObility (SUMO) software. The existing model, based on Eissfeldt's 2004 work, does not fully adhere to the Lig…
-
Genetic algorithm calibrates urban traffic simulations from sparse data
Researchers have developed a new genetic algorithm-based framework to improve urban traffic simulations. This method calibrates simulations using sparse road observations, bypassing the need for detailed employment dist…
-
New reward function improves traffic signal control for lower emissions
Researchers have developed a new Momentum-Based Reward Function (MBRF) for adaptive traffic signal control systems. This novel approach aims to improve urban traffic flow and reduce emissions by encouraging continuous v…
-
Multi-agent LLM framework enhances traffic simulation accuracy
Researchers have developed a new multi-agent framework for generating traffic simulations in SUMO, addressing limitations of monolithic agent architectures. This framework decouples the simulation process into specializ…
-
Smart parking system uses dynamic buffers and reputation to improve reliability
Researchers have developed a novel dual-mechanism architecture to improve the reliability of smart parking reservation systems. The system incorporates a dynamic buffer of non-reservable slots to ensure parking availabi…
-
UCATSC model improves traffic signal control with uncertainty awareness
Researchers have developed UCATSC, a novel decision layer for vision-based traffic signal control that addresses partial observability issues. This system maintains a belief state about traffic conditions and uses count…
-
AI system PALCAS improves autonomous vehicle lane changes with federated reinforcement learning
Researchers have developed PALCAS, a new system for autonomous vehicles that uses federated reinforcement learning to advise on lane changes. Unlike previous systems, PALCAS prioritizes lane changes based on a vehicle's…
-
LLMs enhance traffic signal control with LSTM prediction and safety filters
Researchers have developed a new framework for traffic signal control that leverages large language models (LLMs) combined with LSTM-based traffic state prediction. This system forecasts traffic conditions and uses LLMs…