Real-Time Edge AI-Based Gait-Aware Control System for Wearable Hip Exoskeletons

View at Publisher

Ask AI

Bookmark

Share

Key Points

The aim is to develop a real-time gait-aware control system for wearable hip exoskeletons using an embedded edge AI framework.
Developed an integrated pipeline comprising multimodal sensor data collection, gait mode classification, phase estimation, and torque generation.
Utilized a lightweight gait classification model and optimized temporal convolutional network for phase prediction on an NVIDIA Jetson Orin Nano.
Conducted leave-one-subject-out cross-validation experiments to evaluate performance.
Achieved high gait mode classification accuracy of 96.45 ± 0.33%.
Confirmed real-time operation with an average inference latency of about 2.03ms at a control frequency of 100Hz.
Demonstrated torque profiles consistent with gait cycles across varying conditions.

Demonstrates real-time control of a hip exoskeleton in various gait conditions, highlighting its practical application.

No abstract yet. The journal hasn't published one we can show.

No takes yet. Share an insight, caveat, or question.

Heo et al. (2026) studied this question.

View at Publisher

Ask AI

Bookmark

Share