Related papers: Active Learning from Scene Embeddings for End-to-E…

BEV perception is of great importance in the field of autonomous driving, serving as the cornerstone of planning, controlling, and motion prediction. The quality of the BEV feature highly affects the performance of BEV perception. However,…

We propose UAD, a method for vision-based end-to-end autonomous driving (E2EAD), achieving the best open-loop evaluation performance in nuScenes, meanwhile showing robust closed-loop driving quality in CARLA. Our motivation stems from the…

Vision-language models (VLMs) have recently emerged as powerful representation learning systems that align visual observations with natural language concepts, offering new opportunities for semantic reasoning in safety-critical autonomous…

Autonomous vehicles (AVs) are poised to redefine transportation by enhancing road safety, minimizing human error, and optimizing traffic efficiency. The success of AVs depends on their ability to interpret complex, dynamic environments…

A self-driving perception model aims to extract 3D semantic representations from multiple cameras collectively into the bird's-eye-view (BEV) coordinate frame of the ego car in order to ground downstream planner. Existing perception methods…

We present Flex, an efficient and effective scene encoder that addresses the computational bottleneck of processing high-volume multi-camera data in end-to-end autonomous driving. Flex employs a small set of learnable scene tokens to…

Most approaches for instance-aware semantic labeling traditionally focus on accuracy. Other aspects like runtime and memory footprint are arguably as important for real-time applications such as autonomous driving. Motivated by this…

Event cameras are bio-inspired vision sensors that naturally capture the dynamics of a scene, filtering out redundant information. This paper presents a deep neural network approach that unlocks the potential of event cameras on a…

Semantic segmentation in bird's eye view (BEV) plays a crucial role in autonomous driving. Previous methods usually follow an end-to-end pipeline, directly predicting the BEV segmentation map from monocular RGB inputs. However, the…

Unlike popular modularized framework, end-to-end autonomous driving seeks to solve the perception, decision and control problems in an integrated way, which can be more adapting to new scenarios and easier to generalize at scale. However,…

Conventional end-to-end autonomous driving methods often rely on explicit global scene representations, which typically consist of 3D object detection, online mapping, and motion prediction. In contrast, human drivers selectively attend to…

Recently, the pure camera-based Bird's-Eye-View (BEV) perception removes expensive Lidar sensors, making it a feasible solution for economical autonomous driving. However, most existing BEV solutions either suffer from modest performance or…

Modern cars are incorporating an increasing number of driver assist features, among which automatic lane keeping. The latter allows the car to properly position itself within the road lanes, which is also crucial for any subsequent lane…

Deep Neural Networks trained in a fully supervised fashion are the dominant technology in perception-based autonomous driving systems. While collecting large amounts of unlabeled data is already a major undertaking, only a subset of it can…

Vision-Language Models (VLMs) offer a promising approach to end-to-end autonomous driving due to their human-like reasoning capabilities. However, troublesome gaps remains between current VLMs and real-world autonomous driving applications.…

We present BEVCon, a simple yet effective contrastive learning framework designed to improve Bird's Eye View (BEV) perception in autonomous driving. BEV perception offers a top-down-view representation of the surrounding environment, making…

The high cost of acquiring labels is one of the main challenges in deploying supervised machine learning algorithms. Active learning is a promising approach to control the learning process and address the difficulties of data labeling by…

End-to-end (E2E) autonomous driving (AD) models require diverse, high-quality data to perform well across various driving scenarios. However, collecting large-scale real-world data is expensive and time-consuming, making high-fidelity…

In this work, we consider the problem of learning end to end perception to control for ground vehicles solely from aerial imagery. Photogrammetric simulators allow the synthesis of novel views through the transformation of pre-generated…

Annotated driving scenario trajectories are crucial for verification and validation of autonomous vehicles. However, annotation of such trajectories based only on explicit rules (i.e. knowledge-based methods) may be prone to errors, such as…