scholarly journals On the Road: Route Proposal from Radar Self-Supervised by Fuzzy LiDAR Traversability

AI ◽  
2020 ◽  
Vol 1 (4) ◽  
pp. 558-585
Author(s):  
Michael Broome ◽  
Matthew Gadd ◽  
Daniele De Martini ◽  
Paul Newman
Keyword(s):  
Autonomous Vehicle ◽  
Optimal Path ◽  
Extreme Environments ◽  
Point Clouds ◽  
Learning Approaches ◽  
Weak Supervision ◽  
The Road ◽  
Optimal Path Planning ◽  
Rule Set ◽  
On The Road

This is motivated by a requirement for robust, autonomy-enabling scene understanding in unknown environments. In the method proposed in this paper, discriminative machine-learning approaches are applied to infer traversability and predict routes from Frequency-Modulated Contunuous-Wave (FMCV) radar frames. Firstly, using geometric features extracted from LiDAR point clouds as inputs to a fuzzy-logic rule set, traversability pseudo-labels are assigned to radar frames from which weak supervision is applied to learn traversability from radar. Secondly, routes through the scanned environment can be predicted after they are learned from the odometry traces arising from traversals demonstrated by the autonomous vehicle (AV). In conjunction, therefore, a model pretrained for traversability prediction is used to enhance the performance of the route proposal architecture. Experiments are conducted on the most extensive radar-focused urban autonomy dataset available to the community. Our key finding is that joint learning of traversability and demonstrated routes lends itself best to a model which understands where the vehicle should feasibly drive. We show that the traversability characteristics can be recovered satisfactorily, so that this recovered representation can be used in optimal path planning, and that an end-to-end formulation including both traversability feature extraction and routes learned by expert demonstration recovers smooth, drivable paths that are comprehensive in their coverage of the underlying road network. We conclude that the proposed system will find use in enabling mapless vehicle autonomy in extreme environments.

scholarly journals New Operating Strategies for an On-the-Road Modular, Electric and Autonomous Vehicle Concept in Urban Transportation

2019 ◽  
Vol 10 (4) ◽  
pp. 91
Author(s):  
Christian Ulrich ◽  
Horst E. Friedrich ◽  
Jürgen Weimer ◽  
Stephan A. Schmid
Keyword(s):  
Business Model ◽  
Urban Areas ◽  
Business Models ◽  
Autonomous Vehicle ◽  
Vehicle Concept ◽  
Drive Unit ◽  
The Road ◽  
Business Model Canvas ◽  
Operating Strategies ◽  
On The Road

Today commercial transport in urban areas faces major challenges. These include making optimal use of limited space, avoiding empty trips, meeting driver shortages as well as reducing costs and emissions such as CO2, particulate matter and noise. The mutual acceleration and reinforcement of technological trends such as electrification, digitization and automation may enable new vehicle and mobility concepts that can meet these challenges. One possible vehicle concept is presented in this article. It is based on on-the-road modularization, i.e., a vehicle that can change different transport capsules during operation. The vehicle is divided into an electrically propelled autonomous drive unit and a transport unit. Standardized interfaces between these units enable the easy design of capsules for different uses, while the drive unit can be used universally. Business models and operating strategies that allow optimal use of this vehicle concept are discussed in depth in the article. First, the current situation is analyzed followed by a detailed description of an exemplary business model using a business model canvas. The operating strategies and logistics concepts are illustrated and compared with conventional concepts.

Optimal Collision-Free Path Planning for an Autonomous Multi-Wheeled Combat Vehicle

2017 ◽  
Author(s):  
Amr Mohamed ◽  
Moustafa El-Gindy ◽  
Jing Ren ◽  
Haoxiang Lang
Keyword(s):  
Path Planning ◽  
Potential Field ◽  
Vehicle Dynamics ◽  
Autonomous Vehicle ◽  
Optimal Path ◽  
Vehicle Model ◽  
Optimal Path Planning ◽  
Combat Vehicle ◽  
Planning Algorithm ◽  
Path Planning Algorithm

This paper presents an optimal collision-free path planning algorithm of an autonomous multi-wheeled combat vehicle using optimal control theory and artificial potential field function (APF). The optimal path of the autonomous vehicle between a given starting and goal points is generated by an optimal path planning algorithm. The cost function of the path planning is solved together with vehicle dynamics equations to satisfy the vehicle dynamics constraints and the boundary conditions. For this purpose, a simplified four-axle bicycle model of the actual vehicle considering the vehicle body lateral and yaw dynamics while neglecting roll dynamics is used. The obstacle avoidance technique is mathematically modeled based on the proposed sigmoid function as the artificial potential field method. This potential function is assigned to each obstacle as a repulsive potential field. The inclusion of these potential fields results in a new APF which controls the steering angle of the autonomous vehicle to reach the goal point. A full nonlinear multi-wheeled combat vehicle model in TruckSim software is used for validation. This is done by importing the generated optimal path data from the introduced optimal path planning MATLAB algorithm and comparing lateral acceleration, yaw rate and curvature at different speeds (9 km/h, 28 km/h) for both simplified and TruckSim vehicle model. The simulation results show that the obtained optimal path for the autonomous multi-wheeled combat vehicle satisfies all vehicle dynamics constraints and successfully validated with TruckSim vehicle model.

scholarly journals Obstacle Detection and Safely Navigate the Autonomous Vehicle from Unexpected Obstacles on the Driving Lane

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4719
Author(s):  
Malik Haris ◽  
Jin Hou
Keyword(s):  
Deep Learning ◽  
Autonomous Vehicle ◽  
Research Area ◽  
Visual Navigation ◽  
Obstacle Detection ◽  
The Road ◽  
Markov Random ◽  
Active Research ◽  
On The Road ◽  
Active Research Area

Nowadays, autonomous vehicle is an active research area, especially after the emergence of machine vision tasks with deep learning. In such a visual navigation system for autonomous vehicle, the controller captures images and predicts information so that the autonomous vehicle can safely navigate. In this paper, we first introduced small and medium-sized obstacles that were intentionally or unintentionally left on the road, which can pose hazards for both autonomous and human driving situations. Then, we discuss Markov random field (MRF) model by fusing three potentials (gradient potential, curvature prior potential, and depth variance potential) to segment the obstacles and non-obstacles into the hazardous environment. Since the segment of obstacles is done by MRF model, we can predict the information to safely navigate the autonomous vehicle form hazardous environment on the roadway by DNN model. We found that our proposed method can segment the obstacles accuracy from the blended background road and improve the navigation skills of the autonomous vehicle.

Self-Driving Cars

2020 ◽  
pp. 490-507
Author(s):  
Pooja Jha ◽  
K. Sridhar Patnaik
Keyword(s):  
Traffic Safety ◽  
Autonomous Vehicle ◽  
Technological Advancement ◽  
Social Environments ◽  
Highway Traffic ◽  
National Highway Traffic Safety ◽  
Human Errors ◽  
The Road ◽  
On The Road ◽  
Self Driving Cars

Human errors are the main cause of vehicle crashes. Self-driving cars bear the promise to significantly reduce accidents by taking the human factor out of the equation, while in parallel monitor the surroundings, detect and react immediately to potentially dangerous situations and driving behaviors. Artificial intelligence tool trains the computers to do things like detect lane lines and identify cyclists by showing them millions of examples of the subject at hand. The chapter in this book discusses the technological advancement in transportation. It also covers the autonomy used according to The National Highway Traffic Safety Administration (NHTSA). The functional architecture of self-driving cars is further discussed. The chapter also talks about two algorithms for detection of lanes as well as detection of vehicles on the road for self-driving cars. Next, the ethical discussions surrounding the autonomous vehicle involving stakeholders, technologies, social environments, and costs vs. quality have been discussed.

Self-Driving Robotic Cars

2021 ◽  
pp. 599-631
Author(s):  
Jelena L. Pisarov ◽  
Gyula Mester
Keyword(s):  
Traffic Flow ◽  
Autonomous Vehicle ◽  
Closed Circuit ◽  
Small Scale ◽  
Traffic Patterns ◽  
Complex Environments ◽  
The Road ◽  
Traffic Jams ◽  
Simulation Techniques ◽  
On The Road

Even the behavior of a single driver can have a dramatic impact on hundreds of cars, making it more difficult to manage traffic. While the attempts to analyze and correct the traffic patterns that lead to congestion began as early in the 1930s, it wasn't until recently that scientists developed simulation techniques and advanced algorithms to create more realistic visualizations of traffic flow. In experiments conducted by Alexandre Bayen and the Liao-Cho, which included several dozen cars in a small-scale closed circuit, a single autonomous vehicle could eliminate traffic jams by moderating the speed of every car on the road. In larger simulations, the research showed that once their number rises to 5-10% of all cars in the traffic, they can manage localized traffic even in complex environments, such as merging multiple lanes of traffic into two or navigating extremely busy sections.

Self-Driving Robotic Cars

2022 ◽  
pp. 969-1001
Author(s):  
Jelena L. Pisarov ◽  
Gyula Mester
Keyword(s):  
Traffic Flow ◽  
Autonomous Vehicle ◽  
Closed Circuit ◽  
Small Scale ◽  
Traffic Patterns ◽  
Complex Environments ◽  
The Road ◽  
Traffic Jams ◽  
Simulation Techniques ◽  
On The Road

Even the behavior of a single driver can have a dramatic impact on hundreds of cars, making it more difficult to manage traffic. While the attempts to analyze and correct the traffic patterns that lead to congestion began as early in the 1930s, it wasn't until recently that scientists developed simulation techniques and advanced algorithms to create more realistic visualizations of traffic flow. In experiments conducted by Alexandre Bayen and the Liao-Cho, which included several dozen cars in a small-scale closed circuit, a single autonomous vehicle could eliminate traffic jams by moderating the speed of every car on the road. In larger simulations, the research showed that once their number rises to 5-10% of all cars in the traffic, they can manage localized traffic even in complex environments, such as merging multiple lanes of traffic into two or navigating extremely busy sections.

Construction of Control Algorithm for an Autonomous Vehicle

2001 ◽  
Vol 13 (4) ◽  
pp. 387-394
Author(s):  
Hyung-Eun Im ◽  
◽  
Ichiro Kageyama ◽  
Yoshiyuki Nozaki
Keyword(s):  
Control Algorithm ◽  
Prediction Models ◽  
Autonomous Vehicle ◽  
Risk Level ◽  
Minimum Risk ◽  
Control Motion ◽  
Risk Elements ◽  
The Road ◽  
On The Road ◽  
Risk Potential

In this study, a control algorithm of an autonomous vehicle is proposed on the basis of risk level to simulate control motion of a real driver. The normal traffic situation can be expressed by risk level. The risk level is affected by several risk elements: roadside edges, curves, the other vehicles, obstacles, and so on. Each risk element is represented by an exponential function. The risk elements make risk potential field on the road. It is assumed that the desirable course to follow is determined as the point of minimum risk potential in the cross section of the road. Tree prediction models are examined to predict the future position of vehicle. The change of preview time is considered on the curved road. A lateral and longitudinal control algorithm with the prediction model proposed in this study shows similar control motion to that of a real driver.

Pedestrians’ understanding of fully autonomous vehicles (FAV) intent to stop

2020 ◽  
Vol 64 (1) ◽  
pp. 1931-1932
Author(s):  
Michal Hochman ◽  
Tal Oron-Gilad
Keyword(s):  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Background Color ◽  
Urban Road ◽  
The Road ◽  
Message Type ◽  
On The Road ◽  
Future Work ◽  
Road Crossing ◽  
Distance Conditions

This study explored pedestrians’ understanding of Fully Autonomous Vehicle (FAV) intention and what influences their decision to cross. Twenty participants saw fixed simulated urban road crossing scenes with a FAV present on the road. The scenes differed from one another in the FAV’s messages: the external Human-Machine Interfaces (e-HMI) background color, message type and modality, the FAV’s distance from the crossing place, and its size. Eye-tracking data and objective measurements were collected. Results revealed that pedestrians looked at the e-HMI before making their decision; however, they did not always make the decision according to the e-HMIs’ color, instructions (in advice messages), or intention (in status messages). Moreover, when they acted according to the e-HMI proposition, for certain distance conditions, they tended to hesitate before making the decision. Findings suggest that pedestrians’ decision making to cross depends on a combination of the e-HMI implementation and the car distance. Future work should explore the robustness of the findings in dynamic and more complex crossing environments.

scholarly journals An Integrated Model for User State Detection of Subjective Discomfort in Autonomous Vehicles

Vehicles ◽  
2021 ◽  
Vol 3 (4) ◽  
pp. 764-777
Author(s):  
Dario Niermann ◽  
Alexander Trende ◽  
Klas Ihme ◽  
Uwe Drewitz ◽  
Cornelia Hollander ◽  
...  
Keyword(s):  
Autonomous Vehicles ◽  
Linear Models ◽  
Driving Simulator ◽  
Autonomous Vehicle ◽  
The Road ◽  
Novel Approach ◽  
Driving Scenario ◽  
On The Road ◽  
Using Data ◽  
Subjective Discomfort

The quickly rising development of autonomous vehicle technology and increase of (semi-) autonomous vehicles on the road leads to an increased demand for more sophisticated human–machine-cooperation approaches to improve trust and acceptance of these new systems. In this work, we investigate the feeling of discomfort of human passengers while driving autonomously and the automatic detection of this discomfort with several model approaches, using the combination of different data sources. Based on a driving simulator study, we analyzed the discomfort reports of 50 participants for autonomous inner city driving. We found that perceived discomfort depends on the driving scenario (with discomfort generally peaking in complex situations) and on the passenger (resulting in interindividual differences in reported discomfort extend and duration). Further, we describe three different model approaches on how to predict the passenger discomfort using data from the vehicle’s sensors as well as physiological and behavioral data from the passenger. The model’s precision varies greatly across the approaches, the best approach having a precision of up to 80%. All of our presented model approaches use combinations of linear models and are thus fast, transparent, and safe. Lastly, we analyzed these models using the SHAP method, which enables explaining the models’ discomfort predictions. These explanations are used to infer the importance of our collected features and to create a scenario-based discomfort analysis. Our work demonstrates a novel approach on passenger state modelling with simple, safe, and transparent models and with explainable model predictions, which can be used to adapt the vehicles’ actions to the needs of the passenger.

Sign in / Sign up

Export Citation Format

Share Document