Robust and Context-Aware Real-Time Collaborative Robot Handling via Dynamic Gesture Commands

Chen, Rui; Alvin, Shek,; Liu, Changliu

doi:10.1109/lra.2023.3268586

Cited by 2 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With from the implementation of CG recognition. However, given the ever-increasing volume of data and the demand for lowcost robotic control systems, ensuring high accuracy under limited sample conditions while significantly reducing the algorithm's response time to meet real-time requirements [3][4][5][6] remains a significant challenge.…”

Section: Introductionmentioning

confidence: 99%

Real-time continuous gesture recognition system based on PSO-PNN

Ren,

Gao,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

In the field of Natural Human-Machine Interaction (NHMI), wearable gesture interaction technologies have received considerable attention, particularly Continuous Gesture Recognition (CG). However, CG faces several challenges, including the impact of motion characteristics on gesture recognition and performance that is not sufficiently robust. Traditional algorithms are highly dependent on samples, thus meeting the requirements of low sample volume and high accuracy simultaneously is challenging. To address these challenges, we propose a real-time continuous gesture recognition system based on Particle Swarm Optimization (PSO) and Probabilistic Neural Network (PNN). This system employs Principal Component Analysis (PCA) for signal dimensionality reduction to alleviate computational burden and uses K-means clustering and Pearson Correlation Coefficient (PCC) to extract optimal features for gesture classification. In offline gesture recognition experiments involving six continuous gestures, the algorithm achieved an accuracy rate of 97% with a training set of 300 samples and a runtime of just 31.25ms. Compared to other five algorithms, the proposed algorithm improved accuracy by at least 9% and reduced the runtime by 40.475ms. Moreover, gesture recognition experiments were conducted using different datasets, with the PSO-PNN algorithm achieving an average recognition rate of 90.17%, at least 9.84% higher than other algorithms. Finally, in experiments on online continuous gesture control for robots in complex environments, the PSO-PNN demonstrated real-time performance of 28.56ms and a task completion rate of 90.67%, validating the feasibility of PSO-PNN. This research provides a substantial theoretical and technical foundation for the ongoing enhancement and application of continuous gesture recognition technology.

show abstract

Section: Introductionmentioning

confidence: 99%