Testing Of Autonomous Vehicles Research Articles

Intelligence Testing for Autonomous Vehicles: A New Approach

In this paper, we study how to test the intelligence of an autonomous vehicle. Comprehensive testing is crucial to both vehicle manufactories and customers. Existing testing approaches can be categorized into two kinds: scenario-based testing and functionality-based testing. We first discuss the shortcomings of these two kinds of approaches, and then propose a new testing framework to combine the benefits of them. Based on the new semantic diagram definition for the intelligence of autonomous vehicles, we explain how to design a task for autonomous vehicle testing and how to evaluate test results. Experiments show that this new approach provides a quantitative way to test the intelligence of an autonomous vehicle.

Challenges in Autonomous Vehicle Testing and Validation

Software testing is all too often simply a bug hunt rather than a wellconsidered exercise in ensuring quality. A more methodical approach than a simple cycle of system-level test-fail-patch-test will be required to deploy safe autonomous vehicles at scale. The ISO 26262 development V process sets up a framework that ties each type of testing to a corresponding design or requirement document, but presents challenges when adapted to deal with the sorts of novel testing problems that face autonomous vehicles. This paper identifies five major challenge areas in testing according to the V model for autonomous vehicles: driver out of the loop, complex requirements, non-deterministic algorithms, inductive learning algorithms, and failoperational systems. General solution approaches that seem promising across these different challenge areas include: phased deployment using successively relaxed operational scenarios, use of a monitor/actuator pair architecture to separate the most complex autonomy functions from simpler safety functions, and fault injection as a way to perform more efficient edge case testing. While significant challenges remain in safety-certifying the type of algorithms that provide high-level autonomy themselves, it seems within reach to instead architect the system and its accompanying design process to be able to employ existing software safety approaches.

Fuel economy testing of autonomous vehicles

Environmental pollution and energy use in the light-duty transportation sector are currently regulated through fuel economy and emissions standards, which typically assess quantity of pollutants emitted and volume of fuel used per distance driven. In the United States, fuel economy testing consists of a vehicle on a treadmill, while a trained driver follows a fixed drive cycle. By design, the current standardized fuel economy testing system neglects differences in how individuals drive their vehicles on the road. As autonomous vehicle (AV) technology is introduced, more aspects of driving are shifted into functions of decisions made by the vehicle, rather than the human driver. Yet the current fuel economy testing procedure does not have a mechanism to evaluate the impacts of AV technology on fuel economy ratings, and subsequent regulations such as Corporate Average Fuel Economy targets. This paper develops a method to incorporate the impacts of AV technology within the bounds of current fuel economy test, and simulates a range of automated following drive cycles to estimate changes in fuel economy. The results show that AV following algorithms designed without considering efficiency can degrade fuel economy by up to 3%, while efficiency-focused control strategies may equal or slightly exceed the existing EPA fuel economy test results, by up to 10%. This suggests the need for a new near-term approach in fuel economy testing to account for connected and autonomous vehicles. As AV technology improves and adoption increases in the future, a further reimagining of drive cycles and testing is required.

Implementation and Testing of Autonomous Quad-Rotor Aerial Vehicle by Using Ardu-Pilot

Implementation and Testing of Autonomous Quad-Rotor Aerial Vehicle by Using Ardu-Pilot

Test and Evaluation of Autonomous Ground Vehicles

A preestablished test and evaluation system will benefit the development of autonomous ground vehicles. This paper proposes a design method for a scientific and comprehensive test and evaluation system for autonomous ground vehicles competitions. It can better guide and regulate the development of China's autonomous ground vehicles. The test and evaluation system includes the test contents, the test environment, the test methods, and the evaluation methods. Using a hierarchical design approach, the test content is designed to be stage by stage, moving from simplicity to complexity and from individual modules to the entire vehicle. The hierarchical test environment is established according to the levels of test content. The test method based on multilevel platforms and sensors is put forward to ensure the accuracy of test results. A fuzzy comprehensive evaluation method combined with analytic hierarchy process (AHP) is used for the comprehensive evaluation which can quantitatively evaluate the individual module and the overall technical performance of autonomous ground vehicles. The proposed test and evaluation system has been successfully applied to real autonomous ground vehicle competitions.

Air-Combat Strategy Using Approximate Dynamic Programming

Unmanned aircraft systems have the potential to perform many of the dangerous missions currently flown by manned aircraft, yet the complexity of some tasks, such as air combat, have precluded unmanned aircraft systems from successfully carrying out these missions autonomously. This paper presents a formulation of a level-flight fixed-velocity one-on-one air-combat maneuvering problem and an approximate dynamic programming approach for computing an efficient approximation of the optimal policy. In the version of the problem formulation considered, the aircraft learning the optimal policy is given a slight performance advantage. This approximate dynamic programming approach provides a fast response to a rapidly changing tactical situation, long planning horizons, and good performance, without explicit coding of air-combat tactics. The method's success is due to extensive feature development, reward shaping, and trajectory sampling. An accompanying fast and effective rollout-based policy extraction method is used to accomplish online implementation. Simulation results are provided that demonstrate the robustness of the method against an opponent, beginning from both offensive and defensive situations. Flight results are also presented using unmanned aircraft systems flown at the Massachusetts Institute of Technology's real-time indoor autonomous vehicle test environment.

Real-time indoor autonomous vehicle test environment

To investigate and develop unmanned vehicle systems technologies for autonomous multiagent mission platforms, we are using an indoor multivehicle testbed called real-time indoor autonomous vehicle test environment (RAVEN) to study long-duration multivehicle missions in a controlled environment. Normally, demonstrations of multivehicle coordination and control technologies require that multiple human operators simultaneously manage flight hardware, navigation, control, and vehicle tasking. However, RAVEN simplifies all of these issues to allow researchers to focus, if desired, on the algorithms associated with high-level tasks. Alternatively, RAVEN provides a facility for testing low-level control algorithms on both fixed- and rotary-wing aerial platforms. RAVEN is also being used to analyze and implement techniques for embedding the fleet and vehicle health state (for instance, vehicle failures, refueling, and maintenance) into UAV mission planning. These characteristics facilitate the rapid prototyping of new vehicle configurations and algorithms without requiring a redesign of the vehicle hardware. This article describes the main components and architecture of RAVEN and presents recent flight test results illustrating the applications discussed above.

EXPERIMENTAL AERODYNAMIC PERFORMANCE OF A SELF-TRIMMING WING-SAIL FOR AUTONOMOUS SURFACE VEHICLES

Recent experimental testing of an unmanned autonomous marine surface vehicle has demonstrated several key advances for a wind propelled platform. The HWT-X1, is a winged catamaran based on modified conventional sailing vessel intended for use as surveillance and sensor platform in either littoral or unprotected waters. The novel propulsion system is a vertical wing, suspended on bearings and “flown” aerodynamically using conventional flaps and tails. Experimental validation has shown exceptional pointing performance, with upwind progress at 20-25 degrees to the true wind. Additionally, speeds of 60% of the true wind speed are achieved routinely under wind speeds from 12 - 25 knots.

CONTROL SYSTEM PERFORMANCE OF AN UNMANNED WIND-PROPELLED CATAMARAN

Recent experimental testing of an unmanned autonomous marine surface vehicle has demonstrated several key advances in control system performance for a wind propelled platform. The HWT X-1 is a winged catamaran based on a modified conventional sailing vessel intended for use as a surveillance and sensor platform in either littoral or unprotected waters. Using GPS and an off- the-shelf commercial Attitude and Heading Reference System (AHRS) as the primary sensors, in integrated control architecture has been implemented that has demonstrated closed loop control about a figure-8 course while under wind propulsion. A speed regulation control system maintains a minimum speed on course using a combination of electric drive motors and wind propulsion, reducing power on the drive motors as the wing-sail accelerates the vehicle. Trajectory control is accomplished with line acquisition and line tracking controllers. The line acquisition control uses a line-of-sight guidance law, and acquires the line within 100m. The line tracking controller demonstrated an ensemble mean of 1.0m and a standard deviation of 0.7m for sheltered waters, and mean of 1.6m and a standard deviation of 1.2m for open waters.