Genetic Algorithm for Path Planning of a Mobile Robot in an Obstacle-Filled Environment

Project info

• Field of studyRobotics and Mechatronics
• LevelDoctoral dissertation (S3)
• Method typeOptimisation
• Estimated build time± 7 working days
• Toolsga, optimoptions (Global Optimization Toolbox)
• PriceUS$38 - US$247

Research goal

Optimise the path length with a genetic algorithm by tuning the number of waypoints and the obstacle clearance within realistic constraints.

Variables

Example result

• -0.251Best x
• -1.229Best y
• 1.99Best fitness
• 45Generations
• 1752Function evaluations
• 0Final spread

The genetic algorithm finds Number of waypoints=-0.251 and Obstacle clearance=-1.229 with best Path length=1.990 after 45 generations (1752 evaluations); population spread shrinks from 2.79 to 0.00.

Computed from illustrative synthetic data, not from a real study.

About Genetic Algorithm (ga)

The genetic algorithm in MATLAB (ga) finds a global optimum by evolving a population of solutions without needing derivatives. It suits non-smooth or multi-minimum objectives and design problems with mixed variables.

Steps

1. 1Define the objective and variable bounds
2. 2Set population size, number of generations, and tolerance
3. 3Set options with optimoptions('ga')
4. 4Run ga several times with different seeds
5. 5Collect the best solutions and their variability
6. 6Plot the convergence curve

Assumptions to check

• The objective can be evaluated repeatedly at reasonable cost
• Population and generation settings are large enough
• Results are stochastic, so several runs are needed

Reading and reporting the results

Report ga settings, the mean and standard deviation of best values over several runs, and the best solution. Compare with gradient-based solvers to show the advantage on multimodal problems.

Example MATLAB code

A short starting script with this project's variable names. The delivered version is adapted to your data and fully commented.

path_length = @(x) 20 + sum(x.^2 - 10*cos(2*pi*x));       % Rastrigin function
nvars = 2;  lb = [-5.12 -5.12];  ub = [5.12 5.12];
opts = optimoptions('ga', 'PopulationSize', 80, 'MaxGenerations', 100, ...
    'Display', 'off', 'FunctionTolerance', 1e-10);

nrun = 5;
best = zeros(nrun, 1);  sols = zeros(nrun, nvars);
for r = 1:nrun
    rng(r);
    [sols(r,:), best(r)] = ga(path_length, nvars, [], [], [], [], lb, ub, [], opts);
end
fprintf('Best values over %d runs: %s\n', nrun, mat2str(best', 4));
fprintf('Mean = %.4f, SD = %.4f\n', mean(best), std(best));
[~, ib] = min(best);
number_of_waypoints = sols(ib, :);
fprintf('Best solution: [%.4f %.4f]\n', number_of_waypoints(1), number_of_waypoints(2));

rng(1);
[~, ~, ~, out] = ga(path_length, nvars, [], [], [], [], lb, ub, [], opts);
fprintf('Generations used: %d, function evaluations: %d\n', out.generations, out.funccount);
figure; bar(best); xlabel('Run'); ylabel('Best objective');

Packages and prices

Choose how much help you need. Each higher package includes everything in the lower ones. Prices exclude 11% VAT.

• Payment: 50% down payment before work starts, balance after the deliverables are handed over
• Tax: Prices exclude 11% VAT
• Data and academic integrity: Results are computed from your own research data; you write and stand behind your manuscript, we help with the analysis and your understanding of it
• Revisions: Up to 2 revisions are included in the price (Package 3: 3 rounds)

Frequently asked questions