Testing and Debugging Autonomous Driving: Experiences with Path Planner and Future Challenges

2020 ◽  
Author(s):  
Fuyuki Ishikawa
Keyword(s):  
Autonomous Driving ◽  
Testing And Debugging ◽  
Future Challenges ◽  
Path Planner

scholarly journals Modules and Techniques for Motion Planning: An Industrial Perspective

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 420
Author(s):  
Stefano Quer ◽  
Luz Garcia
Keyword(s):  
Data Fusion ◽  
Autonomous Driving ◽  
Random Trees ◽  
Approximation Techniques ◽  
Main Research ◽  
Autonomous Cars ◽  
Critical Issues ◽  
Relative Errors ◽  
Path Planner ◽  
Many Core

Research on autonomous cars has become one of the main research paths in the automotive industry, with many critical issues that remain to be explored while considering the overall methodology and its practical applicability. In this paper, we present an industrial experience in which we build a complete autonomous driving system, from the sensor units to the car control equipment, and we describe its adoption and testing phase on the field. We report how we organize data fusion and map manipulation to represent the required reality. We focus on the communication and synchronization issues between the data-fusion device and the path-planner, between the CPU and the GPU units, and among different CUDA kernels implementing the core local planner module. In these frameworks, we propose simple representation strategies and approximation techniques which guarantee almost no penalty in terms of accuracy and large savings in terms of memory occupation and memory transfer times. We show how we adopt a recent implementation on parallel many-core devices, such as CUDA-based GPGPU, to reduce the computational burden of rapidly exploring random trees to explore the state space along with a given reference path. We report on our use of the controller and the vehicle simulator. We run experiments on several real scenarios, and we report the paths generated with the different settings, with their relative errors and computation times. We prove that our approach can generate reasonable paths on a multitude of standard maneuvers in real time.

scholarly journals Collaborative Autonomous Driving—A Survey of Solution Approaches and Future Challenges

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3783
Author(s):  
Sumbal Malik ◽  
Manzoor Ahmed Khan ◽  
Hesham El-Sayed
Keyword(s):  
Autonomous Vehicles ◽  
Communication Technologies ◽  
Autonomous Driving ◽  
Use Cases ◽  
Cooperative Driving ◽  
Vehicle To Vehicle ◽  
Future Challenges ◽  
Vehicle To Infrastructure ◽  
High Level ◽  
Intersection Management

Sooner than expected, roads will be populated with a plethora of connected and autonomous vehicles serving diverse mobility needs. Rather than being stand-alone, vehicles will be required to cooperate and coordinate with each other, referred to as cooperative driving executing the mobility tasks properly. Cooperative driving leverages Vehicle to Vehicle (V2V) and Vehicle to Infrastructure (V2I) communication technologies aiming to carry out cooperative functionalities: (i) cooperative sensing and (ii) cooperative maneuvering. To better equip the readers with background knowledge on the topic, we firstly provide the detailed taxonomy section describing the underlying concepts and various aspects of cooperation in cooperative driving. In this survey, we review the current solution approaches in cooperation for autonomous vehicles, based on various cooperative driving applications, i.e., smart car parking, lane change and merge, intersection management, and platooning. The role and functionality of such cooperation become more crucial in platooning use-cases, which is why we also focus on providing more details of platooning use-cases and focus on one of the challenges, electing a leader in high-level platooning. Following, we highlight a crucial range of research gaps and open challenges that need to be addressed before cooperative autonomous vehicles hit the roads. We believe that this survey will assist the researchers in better understanding vehicular cooperation, its various scenarios, solution approaches, and challenges.

scholarly journals Real - Time Trajectory and Velocity Planning for Autonomous Vehicles

2021 ◽  
Vol 10 (5) ◽  
pp. 439-448
Author(s):  
Hrishikesh Dey ◽  
Rithika Ranadive ◽  
Abhishek Chaudhari
Keyword(s):  
Path Planning ◽  
Velocity Profile ◽  
Real Time ◽  
Autonomous Vehicle ◽  
Optimal Path ◽  
Autonomous Driving ◽  
Navigation Algorithm ◽  
Velocity Planning ◽  
Planning Algorithm ◽  
Path Planner

Path planning algorithm integrated with a velocity profile generation-based navigation system is one of the most important aspects of an autonomous driving system. In this paper, a real-time path planning solution to obtain a feasible and collision-free trajectory is proposed for navigating an autonomous car on a virtual highway. This is achieved by designing the navigation algorithm to incorporate a path planner for finding the optimal path, and a velocity planning algorithm for ensuring a safe and comfortable motion along the obtained path. The navigation algorithm was validated on the Unity 3D Highway-Simulated Environment for practical driving while maintaining velocity and acceleration constraints. The autonomous vehicle drives at the maximum specified velocity until interrupted by vehicular traffic, whereas then, the path planner, based on the various constraints provided by the simulator using µWebSockets, decides to either decelerate the vehicle or shift to a more secure lane. Subsequently, a splinebased trajectory generation for this path results in continuous and smooth trajectories. The velocity planner employs an analytical method based on trapezoidal velocity profile to generate velocities for the vehicle traveling along the precomputed path. To provide smooth control, an s-like trapezoidal profile is considered that uses a cubic spline for generating velocities for the ramp-up and ramp-down portions of the curve. The acceleration and velocity constraints, which are derived from road limitations and physical systems, are explicitly considered. Depending upon these constraints and higher module requirements (e.g., maintaining velocity, and stopping), an appropriate segment of the velocity profile is deployed. The motion profiles for all the use-cases are generated and verified graphically.

scholarly journals Investigating Warehousing Operations from an Integrated Supply-Chain and Transportation Approach

2020 ◽  
Vol 5 (5) ◽  
Author(s):  
Sushant Siddharth Wanjari
Keyword(s):  
Big Data ◽  
Supply Chain ◽  
Geographical Location ◽  
Autonomous Driving ◽  
Integrated System ◽  
Transport Costs ◽  
Spatial Understanding ◽  
Organizational Perspective ◽  
Future Challenges ◽  
The Impact

Transportation a primary step in the supply chain of goods. The responsive time between the parts of this chain may critically affect the duration of the processes. By accounting on an integrated system, warehouses can increase the accuracy and reliability of the processes. This paper analyzes the feasibility of integrated transportation and warehousing platforms from two points of view: infrastructure (e.g. physical place, geographical location) and organizational perspective (e.g. software, data, models). This paper contributes to fill the gap between practitioners and researchers about the needs of both systems. This paper found that transportation and warehousing are two inherently linked systems. However, the current practice lacks substantial improvements in data collection and modeling of these systems. Future directions point towards the use of big data and the implementation of econometric concepts (i.e. choice models), together with a spatial understanding of the impact of warehousing locations (i.e. accessibility concept) in transport costs. E-commerce, big data, and autonomous driving are the future challenges to integrating these two systems of warehousing and transportation. Finally, with the current pandemic of COVID-19, improving freight services is becoming a basic need. This paper contributes to a better understanding of the needs of integrating transportation and warehousing in the current challenging times.

scholarly journals Gaussian Process Based Model Predictive Control for Overtaking in Autonomous Driving

2021 ◽  
Vol 15 ◽  
Author(s):  
Wenjun Liu ◽  
Chang Liu ◽  
Guang Chen ◽  
Alois Knoll
Keyword(s):  
Model Predictive Control ◽  
Gaussian Process ◽  
Predictive Control ◽  
Control Strategies ◽  
Autonomous Driving ◽  
Efficient Simulation ◽  
Model Mismatch ◽  
Path Planner ◽  
The Cost ◽  
Geometric Relationship

This paper proposes a novel framework for addressing the challenge of autonomous overtaking and obstacle avoidance, which incorporates the overtaking path planning into Gaussian Process-based model predictive control (GPMPC). Compared with conventional control strategies, this approach has two main advantages. Firstly, combining Gaussian Process (GP) regression with a nominal model allows for learning from model mismatch and unmodeled dynamics, which enhances a simple model and delivers significantly better results. Due to the approximation for propagating uncertainties, we can furthermore satisfy the constraints and thereby the safety of the vehicle is ensured. Secondly, we convert the geometric relationship between the ego vehicle and other obstacle vehicles into the constraints. Without relying on a higher-level path planner, this approach substantially reduces the computational burden. In addition, we transform the state constraints under the model predictive control (MPC) framework into a soft constraint and incorporate it as relaxed barrier function into the cost function, which makes the optimizer more efficient. Simulation results indicate that the proposed method can not only fulfill the overtaking tasks but also maintain safety at all times.

scholarly journals Occlusion-Aware Path Planning to Promote Infrared Positioning Accuracy for Autonomous Driving in a Warehouse

Electronics ◽  
2021 ◽  
Vol 10 (24) ◽  
pp. 3093
Author(s):  
Bai Li ◽  
Shiqi Tang ◽  
Youmin Zhang ◽  
Xiang Zhong
Keyword(s):  
Autonomous Vehicle ◽  
Autonomous Driving ◽  
Reference Line ◽  
Frenet Frame ◽  
Trial And Error ◽  
Curvature Bounds ◽  
Infrared Emitter ◽  
Path Planner ◽  
Error Simulation ◽  
Vehicle Platform

Infrared positioning is a critical module in an indoor autonomous vehicle platform. In an infrared positioning system, the ego vehicle is equipped with an infrared emitter while the infrared receivers are fixed onto the ceiling. The infrared positioning result is accurate only when the number of valid infrared receivers is more than three. An infrared receiver easily becomes invalid if it does not receive light from the infrared emitter due to indoor occlusions. This study proposes an occlusion-aware path planner that enables an autonomous vehicle to navigate toward the occlusion-free part of the drivable area. The planner consists of four layers. In layer one, a homotopic A* path is searched for in the 2D grid map to roughly connect the initial and goal points. In layer two, a curvature-continuous reference line is planned close to the A* path using numerical optimal control. In layer three, a Frenet frame is constructed along the reference line, followed by a search for an occlusion-aware path within that frame via dynamic programming. In layer four, a curvature-continuous path is optimized via quadratic programming within the Frenet frame. A path planned within the Frenet frame may violate the curvature bounds in a real-world Cartesian frame; thus, layer four is implemented through trial and error. Simulation results in CarSim software show that the derived paths reduce the poor positioning risk and are easily tracked by a controller.

Parameter-Based Testing and Debugging of Autonomous Driving Systems

2021 ◽  
Author(s):  
Paolo Arcaini ◽  
Alessandro Calo ◽  
Fuyuki Ishikawa ◽  
Thomas Laurent ◽  
Xiao-Yi Zhang ◽  
...  
Keyword(s):  
Autonomous Driving ◽  
Testing And Debugging

scholarly journals Embracing the Future Internet of Things

Sensors ◽  
2019 ◽  
Vol 19 (2) ◽  
pp. 351 ◽  
Author(s):  
Flavio Cirillo ◽  
Fang-Jing Wu ◽  
Gürkan Solmaz ◽  
Ernö Kovacs
Keyword(s):  
Internet Of Things ◽  
Virtual World ◽  
Smart Cities ◽  
Future Internet ◽  
Autonomous Driving ◽  
The Future ◽  
Future Challenges ◽  
Global Vision ◽  
Status Information ◽  
Open Issues

All of the objects in the real world are envisioned to be connected and/or represented, through an infrastructure layer, in the virtual world of the Internet, becoming Things with status information. Services are then using the available data from this Internet-of-Things (IoT) for various social and economical benefits which explain its extreme broad usage in very heterogeneous fields. Domain administrations of diverse areas of application developed and deployed their own IoT systems and services following disparate standards and architecture approaches that created a fragmentation of things, infrastructures and services in vertical IoT silos. Coordination and cooperation among IoT systems are the keys to build “smarter” IoT services boosting the benefits magnitude. This article analyses the technical trends of the future IoT world based on the current limitations of the IoT systems and the capability requirements. We propose a hyper-connected IoT framework in which “things” are connected to multiple interdependent services and describe how this framework enables the development of future applications. Moreover, we discuss the major limitations in today’s IoT and highlight the required capabilities in the future. We illustrate this global vision with the help of two concrete instances of the hyper-connected IoT in smart cities and autonomous driving scenarios. Finally, we analyse the trends in the number of connected “things” and point out open issues and future challenges. The proposed hyper-connected IoT framework is meant to scale the benefits of IoT from local to global.

scholarly journals Laser-Based People Detection and Obstacle Avoidance for a Hospital Transport Robot

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 961
Author(s):  
Kuisong Zheng ◽  
Feng Wu ◽  
Xiaoping Chen
Keyword(s):  
Obstacle Avoidance ◽  
Single Point ◽  
Autonomous Driving ◽  
Machine Learning Techniques ◽  
People Detection ◽  
Traditional Methods ◽  
Reference Path ◽  
Differential Drive Robot ◽  
Hospital Transport ◽  
Path Planner

This paper describes the development of a laser-based people detection and obstacle avoidance algorithm for a differential-drive robot, which is used for transporting materials along a reference path in hospital domains. Detecting humans from laser data is an important functionality for the safety of navigation in the shared workspace with people. Nevertheless, traditional methods normally utilize machine learning techniques on hand-crafted geometrical features extracted from individual clusters. Moreover, the datasets used to train the models are usually small and need to manually label every laser scan, increasing the difficulty and cost of deploying people detection algorithms in new environments. To tackle these problems, (1) we propose a novel deep learning-based method, which uses the deep neural network in a sliding window fashion to effectively classify every single point of a laser scan. (2) To increase the speed of inference without losing performance, we use a jump distance clustering method to decrease the number of points needed to be evaluated. (3) To reduce the workload of labeling data, we also propose an approach to automatically annotate datasets collected in real scenarios. In general, the proposed approach runs in real-time and performs much better than traditional methods. Secondly, conventional pure reactive obstacle avoidance algorithms can produce inefficient and oscillatory behaviors in dynamic environments, making pedestrians confused and possibly leading to dangerous reactions. To improve the legibility and naturalness of obstacle avoidance in human crowded environments, we introduce a sampling-based local path planner, similar to the method used in autonomous driving cars. The key idea is to avoid obstacles by switching lanes. We also adopt a simple rule to decrease the number of unnecessary deviations from the reference path. Experiments carried out in real-world environments confirmed the effectiveness of the proposed algorithms.

Sign in / Sign up

Export Citation Format

Share Document