Human Trajectory Prediction Model and Its Coupling With a Walking Pattern Generator of a Humanoid Robot

Abstract

In order to smoothly perform interactions between a humanoid robot and a human, knowledge about the human locomotion can be efficiently used. Indeed, in a human-robot collaboration, a prediction model of the human behaviour allows the robot to act proactively. In this paper, an optimal control based model predicting the human Center of Mass (CoM) trajectory during gait is presented. A Walking Pattern Generator (WPG) based on non-linear model predictive control is, then, introduced in order to generate the robot CoM and footsteps along the predicted trajectory. The combination of the human trajectory prediction model and this new WPG aims to allow the robot to proactively walk along with a human instead of passively follow him. These models have been tested in simulation on Gazebo on a TALOS humanoid robot model using measured human trajectories. To perform the CoM and foot trajectories computed by the WPG, a real-time whole-body controller is used. This controller is a Quadratic Program which solves the inverse dynamics of the robot at torque level.

Walking paths during collaborative carriages do not follow the simple rules observed in the locomotion of single walking subjects

“…Thus, the starting hypothesis stating that we could model pairs of humans carrying a table with the same method used to model single walking humans turned out to be wrong. Indeed, the method, which worked well to model 22 and even predict 23 a single human behaviour, did not succeed in building an accurate model for two humans walking with a table. It was not totally unexpected as two humans carrying a table were not two independent holonomous systems coupled through a table.…”

“…Thus, the solution to accurately model the behaviour of a human during a table handling task may be able to model the table behaviour first and then to infer the carriers’ behaviour. Then, a prediction model may be developed based on this trajectory model as it was done in Maroger et al 23 to predict in real-time single walking human trajectories. However, it is important to denote that other approaches, which do not assumed the existence of an optimal trajectory, could have been considered to analyze the performed experiments.…”

“…It was optimized using a bi-level Inverse Optimal Control (IOC) scheme, first introduced in Mombaur et al 21 , to well fit average human CoM trajectories during locomotion. Using a similar OC model which takes as an input the recent past trajectory of a single walking human, it is even possible to accurately predict his future trajectory without knowing his goal position 23 . This kind of model, does not exist, as far as we know, for human walking during collaborative tasks.…”

A Machine Learning Model for Predicting Sit-to-Stand Trajectories of People with and without Stroke: Towards Adaptive Robotic Assistance

“…The literature often highlights how displacements of the centre of mass (CoM) are a predictor and cause of falls [7,22]. Calculating CoM dynamically is computationally expensive, and many studies opt for using simplified human models [38], which has been show to affect the accuracy of resultant predictions [39]. This study focuses on the potential use of robotic assistance to prevent users arriving at an unstable body position that could lead to a fall.…”

Neural Network-Based Channel Estimation and Detection in Spatial Modulation VLC Systems

“…, cm ) T . Considering cm as the initial location and cm+1 as the final location, intermediate device positions are predicted exploiting the path prediction technique in [17]. Next, it is sampled at Kk c T s to obtain device locations for (j c − N w + 1) to j c pilot instances.…”