Simulation systems have become essential to the development and validation of autonomous driving (AD) tech-nologies. The prevailing state-of-the-art approach for simulation uses game engines or high-fidelity computer graphics (CG) models to create driving scenarios. However, creating CG models and vehicle movements (the assets for simulation) remain manual tasks that can be costly and time consuming. In addition, CG images still lack the richness and authenticity of real-world images, and using CG images for training leads to degraded performance. Here, we present our augmented autonomous driving simulation (AADS). Our formulation augmented real-world pictures with a simulated traffic flow to create photorealistic simulation images and ren-derings. More specifically, we used LiDAR and cameras to scan street scenes. From the acquired trajectory data, we generated plausible traffic flows for cars and pedestrians and composed them into the background. The composite images could be resynthesized with different viewpoints and sensor models (camera or LiDAR). The resulting images are photorealistic, fully annotated, and ready for training and testing of AD systems from perception to planning. We explain our system design and validate our algorithms with a number of AD tasks from detection to segmentation and predictions. Compared with traditional approaches, our method offers scalability and realism. Scalability is particularly important for AD simulations, and we believe that real-world complexity and diversity cannot be realistically captured in a virtual environment. Our augmented approach combines the flexibility of a virtual environment (e.g., vehicle movements) with the richness of the real world to allow effective simulation.

集成了腾讯国际领先的游戏技术与云计算，打造MIL/SIL/HIL/VIL/DIL全链路测试平台，荣获2020 全球新能源汽车大会创新技术大奖。

支持OpenX系列国际标准，ASAM组织在国内最早的成员之一。

With the continuous development of smart vehicles, the accuracy requirements of smart vehicles are getting higher and higher, so the simulation test of smart vehicles is becoming more and more important. In the process of developing intelligent vehi-cles, in order to make the simulation test more comprehensive, human factors are taken into account to avoid the experimental scenario caused by human factors encountered by real vehicles in real road tests, so a traffic confrontation test based on PanoSim is designed. In this experiment, the driving signals of the real vehicle and G29 are transmitted to the virtual vehicle in PanoSim. The actual vehicle is the subject vehicle of the experiment, and G29 is the vehicle controlled by human factors. The traffic confrontation of the two vehicles is realized in PanoSim.

Collaborative autonomous vehicles will appear in the near future and will transform deeply road transportation sys-tems, addressing in part many issues such as safety, traffic efficien-cy, etc. Validation and testing of complex scenarios involving sets of autonomous collaborative vehicles are becoming an important challenge. Each vehicle in the set is autonomous and acts asyn-chronously, receiving and processing huge amount of data in real time, coming from the environment and other vehicles. Simulation of such scenarios in real time require huge computing resources. This paper presents a simulation platform combining the real-time OPAL-RT Technologies for processing and parallel computing, and the Pro-SiVIC vehicular simulator from Civitec for realistic simulation of vehicles dynamic, road/environment, and sensors behaviors. The two platforms are complementary and their combin-ing allow us to propose a real time simulator of collaborative au-tonomous systems.

The Simulation is opening new perspectives to enhance AI for Autonomous Driving:

Optimize Current Algorithm Training and Validation Processes

Introduce more flexibility in generating training and validation data

更多

Generate Multi Sensor data automatically with Ground Truth Information

higher test/scenario coverage, increased data sources, improved parallel processing

收起

For a decade, researchers have focused on the development and deployment of road automated mobility. In the development of autonomous driving embedded systems, several stages are required. The first one deals with the perception layers. The second one is dedicated to the risk assessment, the decision and strategy layers and the optimal trajectory planning. The last stage addresses the vehicle control/command. This paper proposes an efficient solution to the second stage and improves a virtual Cooperative Pilot (Co-Pilot) already proposed in 2012. This paper thus introduces a trajectory planning algorithm for automated vehicles (AV), specifically designed for emergency situations and based on the Autonomous Decision-Support Framework (ADSF) of the EU project Trustonomy. This algorithm is an extended version of Elastic Band (EB) with no fixed final position. A set of trajectory nodes is iteratively deduced from obstacles and constraints, thus providing flexibility, fast computation, and physical realism. After introducing the project framework for risk management and the general concept of ADSF, the emergency algorithm is presented and tested under Matlab software. Finally, the Decision-Support framework is implemented under RTMaps software and demonstrated within Pro-SiVIC, a realistic 3D simulation environment. Both the previous virtual Co-Pilot and the new emergency algorithm are combined and used in a near-accident situation and shown in different risky scenarios.

The LIVIC – a research department from INRETS and LCPC – focuses on the development and the evaluation of driving assistance systems. Several years ago, for the needs of its research activity, LIVIC launched the development of a software architecture SiVIC™, which made possible simulation of multi-frequency sensors responses embedded on static or dynamic devices, equipments and vehicles commonly used in ADAS. Raw data from perception systems are then replaced by accurate synthesised data whenever the scenarios for creating these data are too complex, too dangerous to realize or simply because data did not exist. CIVITEC has been created in October 2008 as a spin-out of INRETS and LCPC to focus on industrialisation, development and distribution of Pro-SiVIC – commercial and professional version of SiVIC™ – to the research community and industry. To further streamline the virtual prototyping process, several enhancements have been added including road networks modelling. The ROADS software is owned and developed by LIVIC and based on OpenDRIVE® specifications, an open file format for the logical description of road networks. LIVIC and CIVITEC are currently extending their collaboration in order to add ROADS into the CIVITEC software portfolio.

The increasing levels of software- and data-intensive driving automation call for an evolution of automotive soft-ware testing. As a recommended practice of the Verification and Validation (V&V) process of ISO/PAS 21448, a candidate standard for safety of the intended functionality for road vehicles, simulation-based testing has the potential to reduce both risks and costs. There is a growing body of research on devising test automation techniques using simulators for Advanced Driver-Assistance Systems (ADAS). However, how similar are the results if the same test scenarios are executed in different simulators? We conduct a replication study of applying a Search-Based Software Testing (SBST) solution to a real-world ADAS (PeVi, a pedes-trian vision detection system) using two different commercial simulators, namely, TASS/Siemens PreScan and ESI Pro-SiVIC. Based on a minimalistic scene, we compare critical test scenarios generated using our SBST solution in these two simulators. We show that SBST can be used to effectively generate critical test scenarios in both simulators, and the test results obtained from the two simulators can reveal several weaknesses of the ADAS under test. However, executing the same test scenarios in the two simulators leads to notable differences in the details of the test outputs, in particular, related to (1) safety violations revealed by tests, and (2) dynamics of cars and pedestrians. Based on our findings, we recommend future V&V plans to include multiple simulators to support robust simulation-based testing and to base test objectives on measures that are less dependant on the internals of the simulators.