autonomous driving
PulseAugur coverage of autonomous driving — every cluster mentioning autonomous driving across labs, papers, and developer communities, ranked by signal.
17 day(s) with sentiment data
-
AI forecasting models suffer from training-inference mismatch, new paper finds
Researchers have identified a mismatch between how trajectory forecasting models for autonomous driving are trained and how they are used during inference. Typically, these models are trained using a winner-take-all (WT…
-
UniTeD unifies perception and planning in autonomous driving with diffusion models · 3 sources tracked
Researchers have developed UniTeD, a novel framework that unifies perception and planning in autonomous driving using diffusion models. Unlike previous methods that decouple these tasks, UniTeD enables bidirectional inf…
-
New ASSCG system optimizes LLM use for autonomous driving planning
Researchers have developed a new system called ASSCG to optimize the use of large language models (LLMs) in autonomous driving planning. ASSCG acts as a gatekeeper, making frame-level decisions to refresh, reuse, or sup…
-
China plans 15th Five-Year Plan for intelligent connected new energy vehicles
China's Ministry of Industry and Information Technology (MIIT) is accelerating the development of a "15th Five-Year Plan" for the intelligent connected new energy vehicle industry. This plan aims to drive industrial tra…
-
New CRAX benchmark accelerates safe reinforcement learning evaluations
Researchers have introduced CRAX, a new benchmark designed to accelerate the evaluation of safe reinforcement learning (RL) agents. Built using the MuJoCo XLA physics engine, CRAX offers up to a 100x speedup compared to…
-
HilDA framework advances self-supervised LiDAR pre-training for autonomous driving
Researchers have introduced HilDA, a novel self-supervised pretraining framework designed to enhance LiDAR backbones for autonomous driving applications. This framework leverages Vision Foundation Models (VFMs) for hier…
-
Germany drafts regulations for AI driver assistance systems
Germany is developing new regulations for AI-based driver assistance systems, focusing on autonomous driving features. The goal is to create a framework for the approval and integration of these advanced systems into ve…
-
New RLPR framework enhances radar-to-LiDAR place recognition for autonomous driving
Researchers have developed RLPR, a novel framework for radar-to-LiDAR place recognition designed to enhance all-weather autonomous driving capabilities. The system addresses the challenge of integrating radar data, whic…
-
CausalDrive: Real-time Causal World Models for Autonomous Driving
Researchers have developed CausalDrive, a novel real-time world model designed to enhance autonomous driving simulations. Unlike previous models that require future trajectories of background agents, CausalDrive operate…
-
New HOLO-MPPI framework enhances robotic motion planning
Researchers have developed HOLO-MPPI, a new framework for multi-scenario motion planning in robotics. This approach combines high-level policy learning with low-level stochastic optimal control. The system learns a high…
-
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…
-
New research proposes 'inference outage' metric for edge AI reliability
A new research paper introduces the concept of "inference outage" (InfOut) probability to better evaluate the reliability of edge inference systems. This metric quantifies the likelihood that end-to-end inference accura…
-
Oracle plans $70B capex; HKEX lists 90 biotech & 10 tech firms
Oracle's CFO announced that the company anticipates $70 billion in net capital expenditures for fiscal year 2027, with returns secured by long-term customer contracts. Separately, Hong Kong Stock Exchange data shows 90 …
-
HKEX sees 90 biotech listings; tech chapter attracts AI firms
The Hong Kong Stock Exchange has seen significant activity under its Chapter 18A listing rules, with 90 biotech companies listing and raising HK$142.9 billion since 2018. Additionally, the Chapter 18C mechanism for spec…
-
New framework evaluates simulated rainfall for autonomous driving tests
Researchers have developed a new framework to evaluate the credibility of simulated rainfall in autonomous driving perception tests. The method uses a path-based approach, representing each simulated path with equivalen…
-
Envision4D advances autonomous driving with future scene prediction
Researchers have developed Envision4D, a novel self-supervised framework for predicting future visual scenes in autonomous driving scenarios. This method addresses limitations in existing feed-forward approaches, which …
-
Coop-WD framework boosts autonomous vehicle perception amid V2V communication issues
Researchers have introduced Coop-WD, a novel framework designed to improve cooperative perception in autonomous vehicles by mitigating the effects of vehicle-to-vehicle (V2V) communication impairments. The system employ…
-
AI planning frameworks boost autonomous driving safety
Researchers have developed new AI planning frameworks for autonomous driving that aim to improve safety and real-time decision-making. ConsistencyPlanner utilizes fast-sampling consistency models to generate diverse, pl…
-
LiDAR perception system tackles 360-degree urban autonomous driving
Researchers have developed a 360-degree LiDAR perception system designed for autonomous driving in complex, unstructured urban environments. The system utilizes panoramic processing and rotation-equivariant sparse convo…
-
New benchmark tests MLLMs' visual evidence identification for autonomous driving
Researchers have developed a new benchmark to evaluate how well multimodal large language models (MLLMs) identify the correct visual evidence for their answers, particularly in autonomous driving scenarios. The benchmar…