Industrial Robotics Practice Exam

Collision-free motion planning is typically tackled with strategies that either explore feasible regions of the robot’s configuration space or optimize a trajectory that avoids obstacles. Sampling-based planners like RRT and PRM handle high-dimensional spaces by randomly sampling configurations and building connections that stay away from collisions, which makes them very effective in cluttered environments and scalable to many joints. Optimization-based trajectory planning, meanwhile, casts the problem as minimizing a cost (such as time, energy, or smoothness) subject to constraints, including collision avoidance, and then computes a collision-free path or trajectory that satisfies those constraints. Together, these approaches are widely used because they provide practical ways to guarantee avoidance while accommodating complex robot models and environments. Brute-force search over all joint configurations becomes infeasible as the dimensionality grows, relying solely on reactive control lacks foresight for obstacles, and impedance control focuses on interaction forces rather than producing a complete collision-free plan.