Data Driven Models for Human Motion Prediction in Human-Robot Collaboration

Li, Qinghua; Zhang, Zhao; You, Yue; Mu, Yaqi; Feng, Chao

doi:10.1109/access.2020.3045994

Cited by 31 publications

(14 citation statements)

References 52 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As stated before, it is highly recommended to avoid colliding with obstacles and operators [172], even when the contact is assured to occur safely. This is desirable because avoiding the collision will increase the safety of the overall system and will reduce to their minimum the probable bottlenecks due to safety stops.…”

Section: Discussionmentioning

confidence: 99%

Human-Robot Interaction Review: Challenges and Solutions for Modern Industrial Environments

et al. 2021

View full text Add to dashboard Cite

The demand for collaborative robots is growing in industrial environments due to their versatility and low prices. Thus, more collaborative solutions are emerging for industrial scenarios. However, implementing scenarios where robots work autonomously while synchronizing their operations in a safe industrial environment with shop-floor workers is not easy. To fill the gap existing in the safe implementation of industrial collaborative scenarios, this manuscript presents a review based on five identified challenges that gathers the primary vital aspects to bear in mind while developing applications for them. Thus, a four-level classification is proposed, which collects the identified challenges and the previous developments in the field of human-robot interaction. The five identified challenges pretends to be the missing enabling key for implementing industrial collaborative scenarios in modern industrial plants. Lastly, a discussion and conclusion are exposed to analyze the degree of development in the field and its potential growth.

show abstract

Section: Discussionmentioning

confidence: 99%

Human-Robot Interaction Review: Challenges and Solutions for Modern Industrial Environments

et al. 2021

View full text Add to dashboard Cite

show abstract

“…This section explores the prediction and intention detection in the literature. Mostly, machine learning techniques, such as neural networks [30][31][32], Bayesian methods [32,33], principal component analysis [34], dynamic movement primitive [35], and hidden Markov models [36], have been used. A probabilistic principal component analysis was used for the recognition and prediction of human motion through motion onset detection by relying on a motion detection database of various motion models and an estimation of the execution speed of a motion [34].…”

Section: User Motion Predictionmentioning

confidence: 99%

“…A probabilistic principal component analysis was used for the recognition and prediction of human motion through motion onset detection by relying on a motion detection database of various motion models and an estimation of the execution speed of a motion [34]. Li et al used a Bayesian predictor for the motion trajectory of the human arm in a reaching task by combining early partial trajectory classification and human motion regression in addition to neural networks used to model the non-linearity and uncertainty of human hand motion [32]. A combination of hidden Markov models and probability density functions was used in [36] to model the human arm motion and predict regions of the workspace occupied by the human using a 3D camera.…”

Section: User Motion Predictionmentioning

confidence: 99%

Improving Haptic Response for Contextual Human Robot Interaction

Mugisha

Guda

Chevallereau

et al. 2022

Sensors

View full text Add to dashboard Cite

For haptic interaction, a user in a virtual environment needs to interact with proxies attached to a robot. The device must be at the exact location defined in the virtual environment in time. However, due to device limitations, delays are always unavoidable. One of the solutions to improve the device response is to infer human intended motion and move the robot at the earliest time possible to the desired goal. This paper presents an experimental study to improve the prediction time and reduce the robot time taken to reach the desired position. We developed motion strategies based on the hand motion and eye-gaze direction to determine the point of user interaction in a virtual environment. To assess the performance of the strategies, we conducted a subject-based experiment using an exergame for reach and grab tasks designed for upper limb rehabilitation training. The experimental results in this study revealed that eye-gaze-based prediction significantly improved the detection time by 37% and the robot time taken to reach the target by 27%. Further analysis provided more insight on the effect of the eye-gaze window and the hand threshold on the device response for the experimental task.

show abstract

“…Especially, for the blind navigation scenario, it is challenging to predict human trajectories accurately because human movements are easily affected by several factors, such as the user's acceptance of a navigational aid [29], situational contexts [30], and environmental factors [31]. There have been several machine learning-based approaches to analyze behavior of a user moving with a mobile robot and predict the user's next trajectory [3], [32]- [34]. However, how the learned user behavior model can be reflected in the navigational guidance of the robot and used to optimize the robot policy remains an open question.…”

Section: Related Work a Robotic Aids For Blind Navigationmentioning

confidence: 99%

Sample-Efficient Training of Robotic Guide Using Human Path Prediction Network

Moon

Seo

2022

IEEE Access

View full text Add to dashboard Cite

Training a robot that engages with people is challenging, because it is expensive to involve people in a robot training process requiring numerous data samples. This paper presents 1) a human path prediction network (HPPN), which predicts a user's next movement based on sequentially sensed human response data and 2) an evolution strategy-based robot training method based on virtual human movements generated by the HPPN, which compensates for this sample inefficiency problem. We applied the proposed method to the training of a robotic guide for visually impaired people, which was designed to collect multimodal human response data and reflect such data in selecting the robot's actions. We collected 1,507 real-world episodes for training the HPPN and then generated over 100,000 virtual episodes for training the robot policy. User test results indicate that our trained robot accurately guides blindfolded participants along a goal path. In addition, by the designed reward to pursue both guidance accuracy and human comfort during the robot policy training process, our robot leads to improved smoothness in human motion while maintaining the accuracy of the guidance. This sample-efficient training method is expected to be widely applicable to all robots and computing machinery that physically interact with humans.

show abstract

Data Driven Models for Human Motion Prediction in Human-Robot Collaboration

Cited by 31 publications

References 52 publications

Human-Robot Interaction Review: Challenges and Solutions for Modern Industrial Environments

Human-Robot Interaction Review: Challenges and Solutions for Modern Industrial Environments

Improving Haptic Response for Contextual Human Robot Interaction

Sample-Efficient Training of Robotic Guide Using Human Path Prediction Network

Contact Info

Product

Resources

About