This paper presents experimental results from real-time parameter estimation of a system model and subsequent trajectory optimization for a dynamic task using the Baxter Research Robot from Rethink Robotics. An active estimator maximizing Fisher information is used in real-time with a closed-loop, non-linear control technique known as Sequential Action Control. Baxter is tasked with estimating the length of a string connected to a load suspended from the gripper with a load cell providing the single source of feedback to the estimator. Following the active estimation, a trajectory is generated using the trep software package that controls Baxter to dynamically swing a suspended load into a box. Several trials are presented with varying initial estimates showing that estimation is required to obtain adequate open-loop trajectories to complete the prescribed task. The result of one trial with and without the active estimation is also shown in the accompanying video. Note to Practitioners-This paper experimentally demonstrates the capability of an on-line parameter learning algorithm on the Baxter Research Robot to improve task performance. This type of algorithm could enable automated systems to actively inspect multi-body parts for parametric information including estimation of the robot's own inertias. The method requires known equations of motion for any nonlinear system with uncertain, constant parameters. We show using a series of 18 experimental trials that using the estimation method results in improved task performance for automated dynamical motions given uncertain parameters.
|Original language||English (US)|
|State||Published - Sep 11 2017|
- Maximum likelihood estimation
- Optimal control
- Parameter estimation
ASJC Scopus subject areas