Carla
PulseAugur coverage of Carla — every cluster mentioning Carla across labs, papers, and developer communities, ranked by signal.
8 day(s) with sentiment data
-
New pipeline improves traffic object localization from surveillance cameras
Researchers have developed a new two-stage pipeline for accurately localizing road traffic objects using surveillance camera imagery. This method improves upon standard approaches that often suffer from errors due to pe…
-
New Deterministic World Model Enhances AI Controller Verification
Researchers have developed a Deterministic World Model (DWM) to improve the formal verification of end-to-end image controllers used in safety-critical systems. This DWM maps physical states directly to synthetic camera…
-
New LAIA dataset enhances AI driver interpretability with human attention data
Researchers have introduced LAIA, a new synthetic dataset designed to enhance the interpretability and explainability of end-to-end driving AI models. Collected using the CARLA simulator, LAIA includes over 15 hours of …
-
New FogDrive dataset enhances autonomous driving perception under varied fog conditions
Researchers have introduced FogDrive, a new synthetic dataset designed to improve autonomous driving perception systems under various fog conditions. The dataset, built using the CARLA simulator, features synchronized m…
-
New study evaluates fuzz testing for reinforcement learning agents
A new study on arXiv evaluates fuzz testing methods for reinforcement learning (RL) agents, which are increasingly used in safety-critical applications. The research systematically compares five state-of-the-art fuzzing…
-
New dataset SimBEV2X advances V2X cooperative perception for autonomous vehicles
Researchers have introduced SimBEV2X, a novel synthetic data generation tool and accompanying large-scale dataset designed to advance cooperative perception for autonomous vehicles. Built on the CARLA simulator, SimBEV2…
-
New VLA frameworks advance autonomous driving perception and action planning · 9 sources tracked
Multiple research papers introduce novel frameworks for autonomous driving that integrate vision, language, and action (VLA) capabilities. MATS proposes a multi-modality, multi-task learning approach with adaptive fusio…
-
OpenDriveLab's Li Chen proposes compositional world models for safer AI policies
OpenDriveLab's Li Chen presented a compositional world model approach at RSS 2026, separating prediction and evaluation components for embodied AI policies. This decoupling aims to improve safety and inspectability by a…
-
New hybrid ViL platform validates cooperative perception for autonomous driving
Researchers have developed a hybrid Vehicle-in-the-Loop (ViL) platform that integrates a real vehicle with a CARLA-based digital twin. This platform is designed to validate cooperative perception systems for automated d…
-
New framework creates smaller, safer AI for autonomous driving
Researchers have developed BucketKD, a new knowledge distillation framework designed to create smaller, safer end-to-end motion planning models for autonomous driving. This method discretizes environmental variables int…
-
New method uses generative world models to improve autonomous driving imitation learning
Researchers have developed a novel approach using latent space generative world models to tackle covariate shift in imitation learning for autonomous vehicles. This method employs a transformer-based perception encoder …
-
New research tackles autonomous driving safety with advanced simulators and benchmarks
Researchers are developing new methods and benchmarks to improve the safety and robustness of autonomous driving systems. One approach, MultiSim, uses an ensemble of simulators to identify failure-inducing scenarios tha…
-
New VLM-CASE framework enhances autonomous driving safety with adaptive envelopes
Researchers have developed VLM-CASE, a novel framework designed to enhance the safety and anticipatory capabilities of autonomous driving systems. This framework integrates a vision-language model (VLM), fine-tuned usin…
-
New framework enables zero-shot transfer of VLM-guided RL for autonomous driving
Researchers have developed Sim2Real-AD, a novel framework designed to bridge the gap between simulated and real-world autonomous driving. This system utilizes vision-language models (VLMs) to guide reinforcement learnin…
-
Stitch4D framework enhances 4D urban reconstruction with sparse views
Researchers have developed Stitch4D, a new framework designed to improve 4D reconstruction in urban environments, particularly when camera views are sparse and lack overlap. The method synthesizes intermediate views to …
-
DriveVA model enhances autonomous driving generalization with joint video and action prediction
Researchers have developed DriveVA, a novel autonomous driving world model designed to improve generalization across different datasets and sensor configurations. This model jointly predicts future visual forecasts and …
-
New V2X collective perception framework validated with hybrid testing
Researchers have developed a new probabilistic framework and hybrid validation methodology for vehicle-to-everything (V2X) collective perception (CP) systems. This approach uses a Bayesian fusion algorithm to create a s…
-
V2X collective perception validated with hybrid simulation and real-world testing
Researchers have developed a new probabilistic framework and hybrid validation methodology for vehicle-to-everything (V2X) collective perception (CP) systems. This approach uses a Bayesian fusion algorithm to integrate …
-
New benchmark quantifies camera rig impact on autonomous driving perception
Researchers have developed a new benchmark called Plentiful CARLA Camera Rigs to study the impact of varying camera configurations on autonomous driving perception systems. This benchmark renders identical driving scene…
-
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…