Survey on Cooperative Perception in an Automotive Context

Abstract

The idea of cooperation has been introduced to selfdriving cars about a decade ago with the aim to reduce the occlusion caused by other users or the scene. More recently, the research efforts turned toward cooperative infrastructure bringing a new kind of the point of view as well as more processing power. This paper lies in this new field providing a survey that addresses the cooperative environment. We provide an overview of the architectures available to create such a system as well as the challenges introduced by the cooperation. Later, we review the main blocks involved in the perception: localization, object detection & tracking, map generation. Each block is reviewed under the prism of cooperation. We also provide a Strengths, Weaknesses, Opportunities, and Threats (SWOT) analysis of the cooperative perception as well as a list of related scenarios alongside experimentations. Finally, we list some related datasets before concluding our paper, underlining the perspectives for further works.

Multi-Agent Cooperative Camera-Based Evidential Occupancy Grid Generation

“…Cooperative systems are more and more present in the state of the art of perception in the autonomous driving context [14]. Today, two main categories of cooperative systems exist; vehicle-to-vehicle (V2V) systems [15] and vehicle-toinfrastructure (V2I) systems [3], [4], [5], [6].…”

“…To define if a cell is positive, we compare its value to a threshold. IoU is defined as in equation ( 13) and F1-score is defined in (14).…”

Evidential Trustworthiness Estimation for Cooperative Perception

“…Since then, the European Telecommunications Standards Institute (ETSI) standardized the Cooperative Perception Message (CPM) [6], composed of the sender position, sensor descriptions and a list of objects. It is used in many cooperative approaches, as studied in [4]. A part of the research effort is focused on preventing attacks as CP works on a public network.…”

Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges

“…Several published notable surveys have discussed technologies in this field, such as [25,26,27,28]. Yang et al [25] build an entire intermediate collaborative perception system and discuss the collaboration challenges from different aspects, such as feature map selection, mmWave communications and vehicular edge computing.…”

“…Cui et al [27] provide a comprehensive overview of collaborative methods mainly from the perspectives of sensor information fusion, information sharing strategies and communication technologies in the Internet of vehicles (IoV). Furthermore, Caillot et al [28] introduce the architecture and facilities in a collaborative perception system and discuss three ego perception tasks based on a cooperative view. Despite the thoroughness of these reviews, there are still knowledge gaps to fill.…”