🤖 AI Summary
This work proposes an energy-efficient approach to lower-limb exoskeleton control by embedding a lightweight decision tree model directly within the inertial measurement unit (IMU)—specifically the ST LSM6DSV16X on the shank—leveraging its built-in Machine Learning Core (MLC) for event-driven, on-chip activity recognition. Instead of continuously transmitting raw inertial data to the main microcontroller for motion classification, the IMU processes sensor data locally and sends only the classification result to the exoskeleton controller. This is the first implementation of interrupt-driven motion mode recognition deployed entirely on the IMU side, eliminating the need for custom machine learning code on the host processor. The method significantly reduces system power consumption, communication overhead, and latency while maintaining high recognition robustness across three key locomotion modes: standing, level-ground walking, and stair climbing, thereby extending battery life and enabling low-latency assistive control.
📝 Abstract
This work presents a wearable human activity recognition (HAR) system that performs real-time inference directly inside a shank-mounted inertial measurement unit (IMU) to support low-latency control of a lower-limb exoskeleton. Unlike conventional approaches that continuously stream raw inertial data to a microcontroller for classification, the proposed system executes activity recognition at the sensor level using the embedded Machine Learning Core (MLC) of the STMicroelectronics LSM6DSV16X IMU, allowing the host microcontroller to remain in a low-power state and read only the recognized activity label from IMU registers. While the system generalizes to multiple human activities, this paper focuses on three representative locomotion modes - stance, level walking, and stair ascent - using data collected from adult participants. A lightweight decision-tree model was configured and deployed for on-sensor execution using ST MEMS Studio, enabling continuous operation without custom machine learning code on the microcontroller. During operation, the IMU asserts an interrupt when motion or a new classification is detected; the microcontroller wakes, reads the MLC output registers, and forwards the inferred mode to the exoskeleton controller. This interrupt-driven, on-sensor inference architecture reduces computation and communication overhead while preserving battery energy and improving robustness in distinguishing level walking from stair ascent for torque-assist control.