Designing Multi-Stage Coupled Convex Programming with Data-Driven McCormick Envelope Relaxations for Motion Planning
This work addresses motion planning challenges for multi-limbed robots, but it is incremental as it builds on existing optimization and relaxation techniques.
The paper tackles motion planning for multi-limbed robots by proposing a multi-stage optimization framework with data-driven McCormick envelope relaxations to address nonlinearities, resulting in improved solve times and interpretability validated on a 10 kg hexapod robot.
For multi-limbed robots, motion planning with posture and force constraints tends to be a difficult optimization problem due to nonlinearities, which also present extended solve times. We propose a multi-stage optimization framework with data-driven inter-stage coupling constraints to address the nonlinearity. Both clustering and evolutionary approaches to find the McCormick envelope relaxations are used to find the problem-specific parameters. The learned constraints are then used in the prior stages, which provides advanced knowledge of the following stages. This leads to improved solve times and interpretability of the results. The planner is validated through multiple walking and climbing tasks on a 10 kg hexapod robot.