Process

Planning

You might say: deciding what to do

Planning chooses tasks and collision-free motions that can carry them out.

What it does

Turns a goal into actions and trajectories that a controller can execute.

Ask

Is the plan feasible, safe, and fast enough to compute when the world changes?

What to look for

1. Tasks and collision-free motions
2. Actions and trajectories from a goal
3. Plan changing when the world changes

Parts

• Task planning and execution: Task planning and execution sequences skills such as navigation, detection, grasping, and placement, and handles their outcomes.
• Motion planning: Motion planning searches for a robot path from start to goal while avoiding collisions and respecting constraints.
• Trajectory generation: Trajectory generation adds time to a geometric path and produces positions, velocities, and accelerations within joint limits.
• Learned policy: A learned policy maps observations to actions from demonstrations, reinforcement learning, or both.

Sources

1. Kevin M. Lynch and Frank C. Park, Modern Robotics: Mechanics, Planning, and Control, Chs. 9–10The path planning problem is a subproblem of the general motion planning problem that is concerned with finding a collision-free path between a start and goal configuration.

Use it on your project

teardown-apply: hold "Planning" (planning) from the teardown at https://teardownatlas.com/robotics/ against my project

Paste it into a coding agent that has the teardown skills.

An AI agent wrote this map with the teardown skill. It can contain errors: check the sources before you rely on a part. About and legal