System configuration of Human-in-the-loop Simulation for Level 3 Autonomous Vehicle using IPG CarMaker

2021 ◽  
Author(s):  
Cheok Jun Hong ◽  
Vimal Rau Aparow
Keyword(s):  
Autonomous Vehicle ◽  
System Configuration ◽  
Human In The Loop ◽  
Level 3

Development of an Autonomous Vehicle for the Cyclic Test

2012 ◽  
Vol 197 ◽  
pp. 98-103
Author(s):  
You Jun Choi ◽  
Hee Seok Moon
Keyword(s):  
Performance Test ◽  
Controller Design ◽  
Autonomous Vehicle ◽  
Path Following ◽  
Cyclic Test ◽  
Driving Ability ◽  
Design System ◽  
System Configuration ◽  
Test Road ◽  
Path Following Algorithm

The cyclic test is becoming one of important tests in automotive industry. Various cyclic tests are needed to be done after new concept of product or technology has developed. However it is almost impossible to do same test at same test condition in real situation because it highly depends on test road condition or driving ability of the driver. Therefore, in order to perform same performance test repeatedly, this paper describes about system configuration and path following algorithm for the cyclic test of the autonomous vehicle. The areas discussed in detail include vehicle modification, controller design, system configuration, navigation and path following algorithm. The performance of the test vehicle is also described and evaluated by experiment in real environment.

scholarly journals Bolt-on Autonomous E-Vehicle System

2021 ◽  
Vol 9 (VI) ◽  
pp. 3924-3929
Author(s):  
Mohit Borkar
Keyword(s):  
Life Cycle ◽  
Electric Vehicle ◽  
Product Life Cycle ◽  
Autonomous System ◽  
Autonomous Vehicle ◽  
Obstacle Detection ◽  
Product Life ◽  
Vehicle System ◽  
Stereo Cameras ◽  
Level 3

In this research we have undertaken the task to design and develop a Level - 3 bolt-on autonomous electric vehicle system, which includes lateral and longitudinal controls which means speed and steering. The paper includes the sensors used for obstacle detection and planning in the autonomous vehicle system, and how using stereo cameras reduces the number of sensors needed to be used in the sensor suite. The Autonomous system will be retro-fitted on any existing electric vehicle to make it autonomous and thus increasing its product life cycle.

Autonomous Vehicle Driving via Deep Deterministic Policy Gradient

2019 ◽  
Author(s):  
Wenhui Huang ◽  
Francesco Braghin ◽  
Stefano Arrigoni
Keyword(s):  
Driving Simulator ◽  
Autonomous Vehicle ◽  
Autonomous Driving ◽  
Machine Learning Algorithms ◽  
Gradient Algorithm ◽  
Vehicle Model ◽  
Human In The Loop ◽  
Policy Gradient ◽  
Discrete Action ◽  
Continuous Actions

Abstract Autonomous driving has became one of the most hot trends in artificial intelligence area in recent years thanks to the machine learning algorithms. However, most of the autonomous driving studies are still limited to discrete action space. In this study, we propose to implement Deep Deterministic Policy Gradient algorithm for learning driving behavior over the continuous actions. For this purpose, a driving simulator is employed which interfaces with IPG CarMker software where the virtual environment and dynamical vehicle model can be built. “Human-in-the-loop” is performed in order to gather the data and a neural network which is implemented in Behavior Layer is trained to recognize two different scenarios-forward driving and stop. Based on the scenario the agent is dealing with, the actions are learnt and suggested from the DDPG algorithm. The experimental results show that DDPG algorithm is able to learn the optimal policy with continuous actions reliably for both scenarios.

scholarly journals Advanced Alarm Method Based on Driver’s State in Autonomous Vehicles

Electronics ◽  
2021 ◽  
Vol 10 (22) ◽  
pp. 2796
Author(s):  
Ji-Hyeok Han ◽  
Da-Young Ju
Keyword(s):  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Autonomous Driving ◽  
Manual Control ◽  
Specific Situation ◽  
Questionnaire Data ◽  
Warning Systems ◽  
Human In The Loop ◽  
The Gaze ◽  
Future Goals

In autonomous driving vehicles, the driver can engage in non-driving-related tasks and does not have to pay attention to the driving conditions or engage in manual driving. If an unexpected situation arises that the autonomous vehicle cannot manage, then the vehicle should notify and help the driver to prepare themselves for retaking manual control of the vehicle. Several effective notification methods based on multimodal warning systems have been reported. In this paper, we propose an advanced method that employs alarms for specific conditions by analyzing the differences in the driver’s responses, based on their specific situation, to trigger visual and auditory alarms in autonomous vehicles. Using a driving simulation, we carried out human-in-the-loop experiments that included a total of 38 drivers and 2 scenarios (namely drowsiness and distraction scenarios), each of which included a control-switching stage for implementing an alarm during autonomous driving. Reaction time, gaze indicator, and questionnaire data were collected, and electroencephalography measurements were performed to verify the drowsiness. Based on the experimental results, the drivers exhibited a high alertness to the auditory alarms in both the drowsy and distracted conditions, and the change in the gaze indicator was higher in the distraction condition. The results of this study show that there was a distinct difference between the driver’s response to the alarms signaled in the drowsy and distracted conditions. Accordingly, we propose an advanced notification method and future goals for further investigation on vehicle alarms.

Autonomous Vehicle (AV) Accident Data Analysis: California OL 316 Reports: 2015-2020

2021 ◽  
Author(s):  
Roger L. McCarthy
Keyword(s):  
Autonomous Vehicle ◽  
Self Report ◽  
Crash Frequency ◽  
Crash Data ◽  
Human Driver ◽  
Accident Data ◽  
Level 3 ◽  
Report Data ◽  
Transportation Research ◽  
The University

Abstract Six years (2015-2020) of autonomous vehicle (AV Level 3) crash data from California's (CA) OL 316 collision reports of AV crashes while in the autonomous mode (AM) or disengaged from AM just before the collision, divided by the associated CA AV make and mileage driven in the AM, are compared with the University of Michigan Transportation Research Institute (UMTRI) corrected human driver crash frequency. AV test drivers in CA mandatorily self-report every crash, whereas average drivers underreport minor accidents, so the UMTRI reporting correction factor permits comparison. CA's AV AM mileage is only a few million miles over the last few years, with virtually no police-reported crash data yet available. OL 316 crash consequence data (e.g., damage, injuries, etc.) is anecdotal and inconsistently self-reported. The CA collision report data indicate the CA AV test fleet exhibits multiples of the human crash frequency. Invariably, the AV accidents are the human driver's fault, with a majority being rear collisions. The human drivers appear less able to anticipate the AV's more conservative driving. CA's AV experience predicts more widespread deployment of existing AV technologies is not likely to reduce vehicle crash frequency, at least in the short term, and might well increase it.

Mixed Autonomous/Teleoperation Control of Asymmetric Robotic Systems

2014 ◽  
Vol 2 (1) ◽  
pp. 35-60
Author(s):  
Pawel Malysz ◽  
Shahin Sirouspour
Keyword(s):  
System Design ◽  
Control Strategy ◽  
Autonomous Control ◽  
Robotic Systems ◽  
System Configuration ◽  
Unified Framework ◽  
Human In The Loop ◽  
Force Tracking ◽  
High Level ◽  
And Control

This paper presents a unified framework for system design and control in human-in-the-loop asymmetric robotic systems. It introduces a highly general teleoperation system configuration involving any number of operators, haptic interfaces, and robots with possibly different degrees of mobility. The proposed framework allows for mixed teleoperation/autonomous control of user-defined subtasks by establishing position/force tracking as well as kinematic constraints among relevant teleoperation control frames. The control strategy is hierarchical comprising of a high-level teleoperation coordinating controller and low-level joint velocity controllers. The approach utilizes idempotent, generalized pseudoinverse and weighting matrices in order to achieve new performance objectives that are defined for such asymmetric semi-autonomous teleoperation systems. Three layers of velocity-based autonomous control at different priority levels with respect to human teleoperation are integrated into the framework. A detailed analysis of system performance and stability is presented. Experimental results with a single-master/dual-slave system configuration demonstrate an application of the proposed system design and control strategy.

Sign in / Sign up

Export Citation Format

Share Document