Carla
PulseAugur coverage of Carla — every cluster mentioning Carla across labs, papers, and developer communities, ranked by signal.
7 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 AI models tackle long-horizon planning for autonomous driving
Researchers are developing advanced AI models for autonomous driving, focusing on improving trajectory planning and long-horizon decision-making. Several new frameworks, including ParkingTransformer, TerraTransfer, Alig…
-
PersonaDrive pipeline creates human-style driving agents for simulations
Researchers have developed PersonaDrive, a novel pipeline for creating more human-like non-ego traffic agents in closed-loop driving simulations. This system conditions a vision-language-action (VLA) agent on retrieved …
-
New pipeline generates terabyte-scale datasets for autonomous systems
Researchers have developed a modular pipeline to generate terabyte-scale datasets for training autonomous systems. This pipeline, utilizing the AVstack framework and CARLA simulator, creates ground-truth-labeled data fo…
-
New compact model integrates multiple autonomous driving perception tasks
Researchers have developed a new compact deep learning model for autonomous driving that can perform multiple perception tasks simultaneously. This model integrates semantic segmentation, depth estimation, LiDAR segment…
-
LLM agents generate safety-critical scenarios for autonomous driving
Researchers have developed EvoDrive, a novel framework that uses LLM agents to generate safety-critical scenarios for autonomous driving systems. This approach aims to improve the validation and enhancement of self-driv…
-
New benchmark reveals safety flaws in autonomous driving models
Researchers have introduced Safe2Drive (S2D), a new benchmark designed to evaluate the safety of end-to-end autonomous driving models. S2D includes 100 challenging scenarios, such as work zones and pedestrian jaywalking…
-
New SkyShield benchmark targets UAV safety with 3D occupancy data
Researchers have introduced SkyShield, a new benchmark dataset designed to improve the safety of low-altitude Unmanned Aerial Vehicle (UAV) autonomy. Existing datasets lack sufficient data for the specific challenges of…
-
New datasets and AI methods advance autonomous driving research
Researchers have introduced several new approaches to enhance autonomous driving systems. One paper details TaCarla, a large dataset for end-to-end autonomous driving research, featuring over 2.85 million frames and sup…
-
AI model optimizes autonomous driving latency-accuracy tradeoff
Researchers have developed a novel multi-resolution deep neural network designed to optimize the balance between latency and accuracy in autonomous driving systems. This approach allows the network to dynamically adjust…
-
New SLIM Model Enhances Long-Range Driving Depth Estimation with Sparse LiDAR
Researchers have developed SLIM (Sparse-LiDAR Injected Monocular geometry), a novel approach to enhance monocular depth estimation for long-range driving scenarios. SLIM adapts the MoGe-2 model to directly incorporate s…
-
New framework generates synthetic pedestrian data for autonomous driving
Researchers have developed ARCANE-PedSynth, an open-source framework built on CARLA for generating synthetic datasets of pedestrians. This framework uses a hybrid AI-manual control system to achieve significantly higher…
-
LLM framework enhances autonomous driving safety with world models
Researchers have developed a new closed-loop framework called Reason--Imagine--Act (RIA) to enhance the safety of large language models (LLMs) in autonomous driving. RIA integrates an LLM reasoner with an action-conditi…
-
LACO enables latent communication for collaborative driving
Researchers have developed LACO, a novel training-free paradigm for latent communication in collaborative driving scenarios. This approach addresses challenges like high latency and information loss associated with lang…
-
AI safety thresholds reinterpreted as neuron spiking thresholds
Researchers have proposed a new method for evaluating safety in automated driving systems by modeling safety thresholds as neuron spiking thresholds. This approach uses a spiking neural network (SNN) trained on human br…
-
MTA-RL framework enhances urban driving with multi-modal AI
Researchers have developed MTA-RL, a novel framework that integrates multi-modal transformer-based 3D affordances with reinforcement learning for robust urban autonomous driving. This approach fuses RGB images and LiDAR…
-
AI research advances autonomous driving perception and safety
Researchers are developing advanced AI techniques to improve autonomous driving systems. One approach, CaAD, focuses on causality-aware end-to-end modeling to better predict vehicle and agent interactions, showing stron…
-
InterFuserDVS integrates event cameras to enhance autonomous driving safety
Researchers have developed InterFuserDVS, an enhanced sensor fusion model for autonomous driving that integrates Dynamic Vision Sensors (DVS) with traditional RGB cameras and LiDAR. This novel approach uses a token-base…
-
ReSim model enhances autonomous driving simulation with diverse data
Researchers have developed ReSim, a novel world simulation model designed to enhance autonomous driving scenarios. By combining real-world driving data with simulated non-expert and hazardous behaviors, ReSim improves t…
-
New dataset 'ParkingScenes' released for autonomous parking research
Researchers have introduced ParkingScenes, a new multimodal dataset designed to improve autonomous parking systems. Built using the CARLA simulator, the dataset includes structured parking trajectories and synchronized …