相关论文: GenAD: Generative End-to-End Autonomous Driving

An intelligent agent operating in the real-world must balance achieving its goal with maintaining the safety and comfort of not only itself, but also other participants within the surrounding scene. This requires jointly reasoning about the…

A promise of Generative Adversarial Networks (GANs) is to provide cheap photorealistic data for training and validating AI models in autonomous driving. Despite their huge success, their performance on complex images featuring multiple…

End-to-End (E2E) autonomous driving models have shown growing capability in recent years, with performance improving on increasingly challenging benchmarks. However, modern generative E2E planners still suffer from a substantial number of…

End-to-end autonomous driving with vision-only is not only more cost-effective compared to LiDAR-vision fusion but also more reliable than traditional methods. To achieve a economical and robust purely visual autonomous driving system, we…

Existing solutions for 3D semantic occupancy prediction typically treat the task as a one-shot 3D voxel-wise segmentation perception problem. These discriminative methods focus on learning the mapping between the inputs and occupancy map in…

Deep-learning-based techniques have been widely adopted for autonomous driving software stacks for mass production in recent years, focusing primarily on perception modules, with some work extending this method to prediction modules.…

We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powerful. With minimum training data from humans the system…

World models have attracted increasing attention in autonomous driving for their ability to forecast potential future scenarios. In this paper, we propose BEVWorld, a novel framework that transforms multimodal sensor inputs into a unified…

Generating adversarial scenarios, which have the potential to fail autonomous driving systems, provides an effective way to improve robustness. Extending purely data-driven generative models, recent specialized models satisfy additional…

Navigating dense and dynamic environments poses a significant challenge for autonomous driving systems, owing to the intricate nature of multimodal interaction, wherein the actions of various traffic participants and the autonomous vehicle…

Efficient navigation in dynamic environments requires anticipating how motion patterns evolve beyond the robot's immediate perceptual range, enabling preemptive rather than purely reactive planning in crowded scenes. Maps of Dynamics (MoDs)…

An ego vehicle following a virtual lead vehicle planned route is an essential component when autonomous and non-autonomous vehicles interact. Yet, there is a question about the driver's ability to follow the planned lead vehicle route.…

Decision-making in long-tail scenarios is pivotal to autonomous-driving development, and realistic and challenging simulations play a crucial role in testing safety-critical situations. However, existing open-source datasets lack systematic…

Dynamic Scene Graph Generation (DSGG) focuses on identifying visual relationships within the spatial-temporal domain of videos. Conventional approaches often employ multi-stage pipelines, which typically consist of object detection,…

Understanding the evolution of 3D scenes is important for effective autonomous driving. While conventional methods mode scene development with the motion of individual instances, world models emerge as a generative framework to describe the…

End-to-end optimization has achieved state-of-the-art performance on many specific problems, but there is no straight-forward way to combine pretrained models for new problems. Here, we explore improving modularity by learning a post-hoc…

A multi-modal framework to generate user intention distributions when operating a mobile vehicle is proposed in this work. The model learns from past observed trajectories and leverages traversability information derived from the visual…

Autonomous driving requires an understanding of the static environment from sensor data. Learned Bird's-Eye View (BEV) encoders are commonly used to fuse multiple inputs, and a vector decoder predicts a vectorized map representation from…

End-to-end autonomous driving models generate future trajectories from multi-view inputs, improving system integration but introducing opaque decisions and hard-to-localize risks. Existing methods either rely on auxiliary monitoring models…

For the offline safety assessment of automated vehicles, the most challenging and critical scenarios must be identified efficiently. Therefore, we present a new approach to define challenging scenarios based on a sensor setup model of the…