Simulation is a cornerstone of autonomous driving efforts, allowing testing to occur more rapidly and with signifi- cantly less risk than is possible with hardware platforms alone. Simulation systems must be able to emulate a variety of sensors including cameras and LiDARs in order to allow high-level software such as image processing and path planning to be tested. In this paper, we present a hardware-in-the-loop (HIL) simulation system without real-time constraints. It is based on CARLA to give access to the sensors required to test high level software, and incorporates compute hardware identical to that used on an autonomous vehicle platform in order to provide realistic constraints regarding available processing power. In addition, we explore the Robot Operating System (ROS) based software framework used on the Formula SAE (FSAE) vehicle and its integration with the driving simulator. Finally, we validate the sensor outputs and vehicle dynamics of the simulated system against a physical autonomous driving hardware platform.
12 April 2022 in Renewable and Sustainable Energy Transition
While current implementations of LIDAR-based autonomous driving systems are capable of road following and obstacle avoidance, they are still unable to detect road lane markings, which is required for lane keeping during autonomous driving sequences. In this paper, we present an implementation of semantic image segmentation to enhance a LIDAR-based autonomous ground vehicle for road and lane marking detection, in addition to object perception and classification. To achieve this, we installed and calibrated a low-cost monocular camera onto a LIDAR-fitted Formula-SAE Electric car as our test bench. Tests were performed first on video recordings of local roads to verify the feasibility of semantic segmentation, and then on the Formula-SAE car with LIDAR readings. Results from semantic segmentation confirmed that the road areas in each video frame were properly segmented, and that road edges and lane markers can be classified. By combining this information with LIDAR measurements for road edges and obstacles, distance measurements for each segmented object can be obtained, thereby allowing the vehicle to be programmed to drive autonomously within the road lanes and away from road edges.
The reliability of autonomous vehicles is heavily dependent on their software frameworks, which are required to interface and process data from many different sensors on board the vehicle, perform navigational processes such as path planning and lane keeping, take action to ensure safety and display data to an operator in a useful fashion. These sensors can include a combination of cameras, LiDARs, GPS, IMU, and odometric sensors to achieve positioning and localisation for the vehicle and nearby objects in their environment and can be challenging to integrate. In this paper, we present a hybridised software framework that combines sensor and navigational processing for autonomous driving. Our framework utilises a modular approach for interfacing and safety functionality, whilst navigation and sensor interfaces are implemented as nodes in the robot operating system. Our testing results verify the suitability of our framework by integration with a hardware-in-the-loop simulation system and for fully autonomous field driving.