Evolutionary computation (original) (raw)
Related papers
Automatic Testing of an Autonomous Parking System Using Evolutionary Computation
SAE Technical Paper Series, 2004
The method of evolutionary functional testing allows it to automate testing by transforming the test case design into an optimization problem. For this aim it is necessary to define a suitable fitness function. In this paper for an autonomous parking system two different approaches for fitness functions are presented, which evaluate the quality of parking maneuver automatically. A numerical analysis shows, that the proposed area criterion supports a faster convergence of the optimization compared to the proposed distance criterion and that the proposed area criterion describes an efficient method to find functional errors in an automated way.
Lecture Notes in Computer Science, 2004
The method of evolutionary functional testing allows for the automation of testing by transforming the test case design into an optimization problem. For this aim it is necessary to define a suitable fitness function. In this paper two different fitness functions are compared for the testing of an autonomous parking system. The autonomous parking system is executed with the generated test scenarios, the fitness for each test scenario is calculated on basis of an evaluation of the quality of the parking maneuver calculated by the autonomous parking system. A numerical analysis shows, that the proposed area criterion supports a faster convergence of the optimization compared to the proposed distance criterion and that the proposed area criterion describes an efficient method to find functional errors in the system in an automated way.
Evolutionary functional testing of an automated parking system
… International Conference on Information Systems …, 2003
Evolutionary Testing is a promising approach for automating the testing of software-based systems. A number of papers have been published in the last years which have successfully applied evolutionary algorithms for test data generation. However, none of these papers address functional testing -the testing of the system's logical behavior on the basis of the system specification -which is, in practice, the most important and most common class of the methods. In this work we present the application of evolutionary testing to the functional testing of an automatic parking system which could automate the parking procedure in future cars. A test environment is described which automatically generates interesting driving maneuvers, performs a simulation of the system with the generated maneuvers and continuously improves the test quality.
Multi-Objective Evolutionary Algorithm -assisted automated parallel parking
2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence), 2008
Abst ract -The ease w i th w hi ch a hum an expert dri ver perform s the com pl ex tasks i nvol ved i n paral l el -parki ng a nonhol onom i c vehi cl e m oti vates the m i m i cry of an hum an dri vi ng behavi or i n autom ati on of the task. Thi s paper presents such an al gori thm to achi eve autom ated paral l el parki ng i n ti ght spaces. U nl i ke other approaches rooted i n neural netw orks and/ or fuzzy l ogi c, the proposed al gori thm perform s m aneuvers cl osel y m odel ed after hum an dri vi ng i nstructi ons. Stevens' pow er l aw i s em pl oyed i n m odel i ng percei ved physi cal quanti ti es on w hi ch the i nstructi ons operate w hi l e the uncertai nty i nherent in the natural l anguage form ul ati on i s represented by G aussi an di stri buti on.
A Genetic Algorithm Approach to Autonomous Smart Vehicle Parking system
Procedia Computer Science
The shopping malls are source of entertainment and pleasure for the public during weekends. People struggling to park their vehicle in parking bay of shopping mall is a usual scenario witnessed at those peak times. Customer precious time and fuel is wasted and they get only few time for shopping. Authorities find it difficult to cope up with this situation even after appointing more employees to manage the traffic experienced in the bay. A smart car parking system that could elevate this problem is an urgent requirement for the shopping mall. This paper falls light on this issue by proposing a new prototype for the smart vehicle parking system. A genetic algorithm approach has been taken to address the issue of scheduling the vehicle to the parking bay.
Lecture Notes in Computer Science, 2015
Making the transition from simulation to reality in evolutionary robotics is known to be challenging. What is known as the reality gap, summarizes the set of problems that arises when robot controllers have been evolved in simulation and then are transferred to the real robot. In this paper we study an additional problem that is beyond the reality gap. In simulations, the robot needs no protection against damage, while on the real robot that is essential to stay cost-effective. We investigate how the probability of collisions can be minimized by introducing appropriate penalties to the fitness function. A change to the fitness function, however, changes the evolutionary dynamics and can influence the optimization success negatively. Therefore, we detect a tradeoff between a required hardware protection and a reduced efficiency of the evolutionary optimization process. We study this tradeoff on the basis of a robotics case study in autonomous parallel parking.
Evolutionary software for autonomous path planning
1999
This research project demonstrated the effectiveness of using evolutionary software techniques in the development of path-planning algorithms and control programs for mobile vehicles in radioactive environments. The goal was to take maximum advantage of the programmer's intelligence by tasking the programmer with encoding the measures of success for a path-planning algorithm, rather than developing the path-planning algorithms themselves. Evolutionary software development techniques could then be used to develop algorithms most suitable to the particular environments of interest. The measures of path-planning success were encoded in the form of a fitness function for an evolutionary software development engine. The task for the evolutionary software development engine was to evaluate the performance of individual algorithms, select the best performers for the population based on the fitness function, and breed them to evolve the next generation of algorithms. The process continued for a set number of generations or until the algorithm converged to an optimal solution. The task environment was the navigation of a rover from an initial location to a goal, then to a processing point, in an environment containing physical and radioactive obstacles. Genetic algorithms were developed for a variety of environmental configurations. Algorithms were simple and non-robust strings of behaviors, but they could be evolved to be nearly optimal for a given environment. In addition, a genetic program was evolved in the form of a control algorithm that operates at every motion of the robot. Programs were more complex than algorithms and less optimal in a given environment. However, after training in a variety of different environments, they were more robust and could perform acceptably in environments they were not trained in. This paper describes the evolutionary software development engine and the performance of algorithms and programs evolved by it for the chosen task.
08351 Summary -- Evolutionary Test Generation
From September 24th to September 29th 2008 the Dagstuhl Seminar 08351 "Evolutionary Test Generation " was held in Schloss Dagstuhl -Leibniz Center for Informatics. During the seminar, several participants presented their current research, and ongoing work and open problems were discussed. This paper contains an executive summary of the seminar and the open problems that were found. The goal of our seminar was to bring together researchers from the software testing and evolutionary algorithms communities for the discussion of problems and challenges in evolutionary test generation. This goal has been satisfactorily met and has led to a comprehensive list of open problems and challenges identified and discussed during the seminar. This list in described in Section 3 of this executive summary.
Evolutionary Strategies as a Verification and Validation Tool
2003
This is a methodology proof-of-concept paper that describes the use of evolutionary algorithms to improve verification and validation (V&V) of a model simulation. Evolutionary algorithms (EAs) have two characteristics useful for V&V. First, they search a broad range of values in the model’s parameter space. This allows testing of unusual combinations of parameter values that might not be found by more conventional bounds checking and sensitivity analysis. Second, they exploit with Darwinian ruthlessness any slight evolutionary advantage shown by these combinations, whether or not these combinations of parameter values were intended or anticipated by the designer. This exploitation might, for instance, drive use of a required resource to zero, if the production rules were incorrect or improperly coded. The original contribution to this paper is to identify a new tool for V&V. It is important because it provides a complimentary approach to conducting bounds checking and sensitivity an...