Intent aware adaptive admittance control for physical Human-Robot Interaction

Abstract

Effective physical Human-Robot Interaction (pHRI) needs to account for variable human dynamics and also predict human intent. Recently, there has been a lot of progress in adaptive impedance and admittance control for human-robot interaction. Not as many contributions have been reported on online adaptation schemes that can accommodate users with varying physical strength and skill level during interaction with a robot. The goal of this paper is to present and evaluate a novel adaptive admittance controller that can incorporate human intent, nominal task models, as well as variations in the robot dynamics. An outer-loop controller is developed using an ARMA model which is tuned using an adaptive inverse control technique. An inner-loop neuroadaptive controller linearizes the robot dynamics. Working in conjunction and online, this two-loop technique offers an elegant way to decouple the pHRI problem. Experimental results are presented comparing the performance of different types of admittance controllers. The results show that efficient online adaptation of the robot admittance model for different human subjects can be achieved. Specifically, the adaptive admittance controller reduces jerk which results in a smooth human-robot interaction.

A dynamical system approach for detection and reaction to human guidance in physical human–robot interaction

“…Interactions with the environment are usually considered passive while the human is an active agent who intends to inject energy into the system. The literature on variable compliance control offers different approaches where the controller adapts to detected human intentions (Lecours et al 2012;Kim et al 2017;Ranatunga et al 2015;Corteville et al 2007). However, such works are limited to a single role for the robot, and human-interaction detection is not used to switch from leader to follower.…”

A User Study on Personalized Stiffness Control and Task Specificity in Physical Human–Robot Interaction

“…This prediction is thereafter used to adapt the robot's objective to user objective to coordinate the interaction. Ranatunga et al (2015) try to account for the variability in human dynamics and propose a controller that can incorporate human intent, nominal task models, as well as variations in the robot dynamics. The proposed scheme consists of an outerloop model tuned using an inverse control technique and an innerloop that uses a neuroadaptive controller to linearize the robot dynamics.…”

Adaptive physical human-robot interaction (PHRI) with a robotic nursing assistant.

“…al. [16,17,[44][45][46]. It has been further improved upon by addition of HIE and prescribed error dynamics (PED) by Cremer et.…”

“…In our recent work, we have expanded these ideas to physical HRI studies with robot arms, in which the interaction admittance is adapted concurrently with the robot model to match a given interaction task model. The resulting Neuro-Adaptive Controller (NAC) structure leads to a model-free control scheme for robots [44,45]. This section describes in detail the BAPI controller in three parts: 1) System dynamics of a robot arm equipped with a BFTS, 2) Neuro-Adaptive Controller or NAC for estimation of robot dynamics and 3) Base Forces Estimator or BFE for identification of interaction forces exerted by the robot arm.…”

“…This idea has also been further investigated in our recent work, where the control scheme is expanded to be used in pHRI scenarios. A Neuro-Adaptive Controller (NAC) was formulated which resulted in model-free control of the robot [44,45]. Our recently proposed Base-sensor Assisted Physical Interaction (BAPI) controller, utilizes NAC and an additional neural network (NN) to estimate the dynamic forces experienced by BFTS [6].…”