To handle the issue of preventing emergencies for motion planning in autonomous driving, we present a novel parallel motion planning framework. Artificial traffic scenes are firstly constructed based ...on real traffic scenes. A deep planning model which can learn from both real and artificial scenes is developed and used to make planning decisions in an end-to-end mode. To prevent emergencies, a generative adversarial networks (GAN) model is designed and learns from the artificial emergencies from artificial traffic scenes. During deployment, the well-trained GAN model is used to generate multiple virtual emergencies based on the current real scene, and the well-trained planning model simultaneously makes different planning decisions for both virtual scenes and the current scenes. The final planning decision is made by comprehensively analyzing observations and virtual emergencies. Through parallel planning, the planner can timely make rational decision without a large number of calculations when an emergency occurs.
On 27 June 2018, the International Parallel Driving Alliance (iPDA) inaugural conference was held in Changshu, China. The iPDA consists of 24 well-known institutions, e.g., the University of ...Cambridge, Purdue University Indianapolis, and the Royal Institute of Technology of Sweden. The iPDA aims to co-establish a common shared research platform for parallel driving and a timely exchange of the latest research results and data related to parallel driving. During the conference, participants discussed the definition, applications, and future challenges of parallel driving and generally agreed that it is a solution to the current autonomous driving problem. Five keynote speakers presented parallel driving with intelligent vehicle theme talks to share their perspectives, field applications, and outlooks on industry trends and future research.
The operational design domain (ODD) of an automated driving system (ADS) can be used to confine the environmental scope of where the ADS is safe to execute. ODD acclimatization is one of the ...necessary steps for validating vehicle safety in complex traffic environments. This article proposes an approach and architectural design to extract and enhance the ODD of the ADS based on the task scenario and the corresponding requirements in the development and verification cycle. The ODD is tightly focused on a unified quantifiable environmental model in the proposed approach while overseeing the ODD extraction process by formal specifications. In addition to the acclimatization framework, an implementation of the proposed approach is examined with two learning-based agents to demonstrate its feasibility. The proof of concept has shown promising directions for future work on ODD monitoring and on the applications in iterative development for ADSs.
Driver anger has become a severe transportation problem resulting in significant injuries and fatalities. The rapid development of intelligent transportation systems has provided new opportunities ...for dynamic angry driving regulations. However, the regulation qualities of different visual attributes under different parameters are not yet clear. In this article, we investigate the anger regulation quality of different parameters for different visual attributes during driving (color: cold/warm; symbol: flat/simulated; expression: positive/negative). Twenty-one drivers drove nine times ( N = 189) on a simulated highway scene with the data recording. The regulation quality of the drivers' anger was analyzed from their subjective experience, behavior, and physiology. Results indicate that regulation driving with different visual attributes presented better driver anger regulation quality compared with baseline driving. Additionally, for the color attribute, the regulation quality of the cold hue was better than the warm hue, and for the expression attribute, the positive expression was better than the negative expression. Our results provide preliminary insights for three specific visual attributes of a driver's anger regulation and compare their corresponding regulation qualities under different parameter changes. Our research provides empirical evidence for choosing different parameters among the three specific visual attributes in the early stages of designing a visual human-machine interface for driver anger.
Affective human-vehicle interaction of intelligent cockpits is a key factor affecting the acceptance, trust, and experience for intelligent connected vehicles. Driver emotion detection is the premise ...of realizing affective human-machine interaction. To achieve accurate and robust driver emotion detection, we propose a novel brain-inspired framework for on-road driver emotion detection using facial expressions. Then, we conduct driver emotion data collection in an on-road context. We develop a data annotation tool, annotate the collected data, and obtain the RoadEmo dataset, a dataset of facial expressions and road scenarios under the driver's emotional driving. Finally, we validate the detection accuracy of the proposed framework. The experiment results show that our proposed framework achieves excellent detection performance in the on-road driver emotion detection task and outperforms existing frameworks.
On June 11th, 2017, the 28th IEEE Intelligent Vehicles Symposium (IV'2017) was held in Redondo Beach, California, USA. As one of the 8 workshops at IV'2017, the cyber-physical-social systems ...(CPSS)-based parallel driving (WS'08), organized by the State Key Laboratory for Management and Control of Complex Systems (SKL-MCCS), Institute of Automation, Chinese Academy of Sciences, China, Xi'an Jiaotong University, China, Tsinghua University, China, Indiana University-Purdue University Indianapolis, USA, and Cranfield University, U.K, has attracted both researchers and practitioners in intelligent vehicles. About 60-70 participants from various countries had extensive and deep discussions on definition, challenges and alternative solutions for CPSS-based parallel driving, and widely agreed that it is a novel paradigm of cloud-based automated driving technologies. Six speakers shared their ideas, studies, field applications, and vision for future along these emerging directions from software-defined vehicles to self-driving vehicles.
The preparation of intelligent-responsive materials with controllable topology structure has long been a significant objective for chemists in the field of materials science. In this paper, we ...designed and prepared a linear-cyclic reversible topological structure polymer based on the bistable 1rotaxane molecular shuttle. A ferrocene-functionalized 1rotaxane and naphthalimide fluorophore group are introduced into the both ends of the polymer, which exhibit distance-induced photo-electron transfer effect. The structural transformation between linear and cyclic state of polymer is demonstrated by simple acid-base stimuli, accompanying visual fluorescence changes. The transformation process was characterized by 1H NMR spectra and fluorescence spectra. This work provides a novel strategy to construct functionalized polymers with topological structure.
Here, we designed and prepared a linear-cyclic reversible topological structure polymer based on the bistable 1rotaxane molecular shuttle. A ferrocene-functionalized 1rotaxane and naphthalimide fluorophore group are introduced into the both ends of the polymer, which exhibit distance-induced photo-electron transfer effect. The structural transformation between linear and cyclic state of polymer is demonstrated by simple acid-base stimuli, accompanying visual fluorescence changes. Display omitted
PDF
