genetic_algorithm_optimization
Apply a genetic algorithm to optimize spacecraft trajectories, evolving solutions through selection, crossover, and mutation.
Instructions
Optimize spacecraft trajectory using genetic algorithm.
Args: optimization_problem: Problem definition (objective, constraints, variables) ga_parameters: Optional GA parameters (population_size, generations, etc.)
Returns: JSON string with optimization results including best solution found, convergence history, and final objective value.
Raises: No exceptions are raised directly; errors are returned as formatted strings.
Note: The GA operates on a population of candidate solutions through: 1. Selection: Tournament or roulette-wheel selection of parents. 2. Crossover: Combining parent chromosomes (e.g., single-point or uniform crossover) to produce offspring that inherit traits from both. 3. Mutation: Random perturbation of offspring genes with probability p_mutation to maintain diversity and avoid premature convergence. Each generation evaluates fitness, selects the best, and breeds the next generation until convergence or max generations reached.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"optimization_problem": "<optimization_problem>"
},
"name": "genetic_algorithm_optimization"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| optimization_problem | Yes | ||
| ga_parameters | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |