Modern cars, trucks, SUVs, and other vehicles have intelligent active suspension systems that adapt to changing terrain conditions. They can adjust in real time to ensure safety and performance. They are expensive and complicated, so they only work well on high-end cars. It is therefore impressive that Jallson Suyo was able add a similar smart suspension adjustment to his bicycle.
Only certain bicycles with suspension forks can this system work. The servo-driven mechanism attaches to the fork and turns a knob to adjust the rebound and firmness of the front suspension. The rider would normally need to stop and adjust the knob manually, but the system can do this automatically based on current conditions. It can accommodate five conditions: sprint, medium, rough, smooth and rough.
Suryo’s project has a lot of interest because it uses machine learning to recognize the conditions and monitors the Arduino Nano 33 BLE Sensor’s nine-axis inertial sensor. Suryo did not have to program specific sensor reading classifications. The Edge Impulse Studio machine learning model was trained using real-world data collected through the Arduino Science Journal App. For example, he could ride on rough trails and tell the model the inertial sensor readings it is seeing correspond to this mode.
The Arduino receives power from a lithium battery via a SparkFun charger/booster board. It runs the trained and deployed Edge Impulse ML model. When it detects inertial sensor readings that indicate a specific terrain or action, it turns the servo to adjust the suspension knob to the ideal setting.
The post Add ML-controlled smart suspension adjustment to your bicycle appeared first on Arduino Blog.