Panasonic develops technology to streamline motion teaching for robots
Panasonic Holdings Corporation has developed a new technology that can teach robots motions that include contact with the surrounding environment (doors, tables, and more) and control parameters that achieve both performance that correctly completes the taught motion and safety during contact.
As the use of industrial robots advances, technology for efficiently programming robot movements is becoming more and more important. In particular, in environments involving contact with people and objects, movements that reduce the risk of contact while performing tasks accurately are required, but robot control that achieves both is known to be extremely difficult. Therefore, Panasonic developed a method to efficiently program a robot assuming it behaves flexibly like a spring. A novel method to learn stiffness parameters of impedance control to satisfy both task performance and safety requirements was developed by segmenting the motions taught to robots demonstrated by humans and multi-objective Bayesian optimization.
This technology has been recognized internationally, and it has been accepted to the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2023, a top conference for AI and robotics technology. It will be presented at the plenary session to be held in Detroit, Michigan in the USA from October 1 to October 5, 2023.
Overview — teaching robots motion
Direct teaching, in which humans directly teach robots movements, is widely used as a method of programming robot movements because of its simplicity. However, when a robot reproduces a taught action in an environment where there is contact with objects or where people or other robots cooperate or divide labor, it becomes necessary to deal with the risk of unforeseen contact in order to avoid damage to people, objects, or the robot itself, making it difficult to utilize robots for certain tasks.
Control technology for flexibly moving robots uses impedance control, which mimics a virtual spring system and gives the robot flexibility. If an appropriate spring system parameter (impedance gain) is set, it is possible to reduce the risk of contact while having the instructed operation performed accurately. However, with impedance control, there is generally a trade-off between safety and motion accuracy, and it is difficult to set an impedance gain that optimizes both at the same time.
Further, in order to achieve the desired task, it is necessary for robots to accurately perform multiple consecutive actions. For example, in the case of opening a door, the robot must 1) approach the knob, 2) turn the knob, and 3) open the door. However, optimum impedance gain differs for each operation.
Therefore, as shown in the Figure 1, Panasonic developed a method that first segments a series of motions being taught to facilitate parameter optimization, and then finds the optimal impedance gain for each segment using multi-objective Bayesian optimization.
Figure 1: Flow of learning impedance control parameters with the newly developed method. Photographs and segmentations illustrate the table wiping task done by an actual robot. Quoted from Figure 1 of the accepted paper.
First, the newly developed task segmentation method IC-SLD (Impedance Control-aware Switching Linear Dynamics) assumes that a series of demonstrated motions is generated by multiple combinations of spring system motion equations for impedance control, and defines this as the problem of inferring the unknown impedance gain and the switching time of the equation. IC-SLD solves this problem by minimizing the error between the predicted trajectory and the actual taught trajectory. Compared with conventional methods such as the Gaussian Mixture Model (GMM) or Switching Linear Dynamics (SLD), IC-SLD realized segmentation is suitable for optimization.
Subsequently, the impedance gain is explored through Bayesian optimization using prior knowledge. Since IC-SLD also outputs an estimated value of the impedance gain, using this as a solution candidate makes optimization more efficient. By applying Bayesian optimization π-BO [Hvarfner+, ICLR2022] that is able to make use of prior knowledge, optimal impedance gains that simultaneously optimize task performance (the cumulative sum of reward functions) and safety indices (the cumulative sum of stiffness parameters) are searched while repeating robot motion trials.
Experiments on simulated tasks and a real robot demonstrated that our method allows for learning the impedance gain in a shorter time than the conventional method.
Figure 2: Segmentation results for the door opening task performed using IC-SLD and the conventional method. Quoted from Figure 4 of the accepted paper.
Figure 3: Learning results of impedance gain in simulation and actual equipment using the newly developed method. The horizontal axis is the number of trials, and the vertical axis is an index that combines task performance and safety. Quoted and processed from Figure 3 and Figure 8 of the accepted paper.
Looking ahead
The newly developed robot teaching technology accelerates the use of robots in environments where they collaborate with humans. We will continue to accelerate the social implementation of AI and robotics, and promote the research and development of AI technology that contributes to our customers’ lives and work sites.
“Learning Compliant Stiffness by Impedance Control-Aware Task Segmentation and Multi-Objective Bayesian Optimization with Priors”, to appear in IROS 2023
https://arxiv.org/abs/2307.15345.
IROS 2023 official website: https://ieee-iros.org
Panasonic×AI website: https://tech-ai.panasonic.com/en
Robotics Hub website: https://tech.panasonic.com/global/robot
https://holdings.panasonic/global
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
