Autonomous Motorcycle-Riding Humanoid Robot to Best Rossi on the Racetrack
Vehicle Used: YZF-R1M
Reference vehicle (Export specification vehicle)
MOTOBOT is an autonomous motorcycle-riding humanoid robot that approaches riding operations from a human rider’s standpoint — with no modifications made to the motorcycle itself. The development theme is “Beyond Human Capabilities.” In general, robots are developed to specialize in a specific task and this typically allows them to surpass the capability of humans for that task. Utilizing this advantage, the end goal of MOTOBOT is to become capable of competing against Valentino Rossi’s lap times around a racetrack. The knowledge and highly advanced fundamental technologies gained from this challenge will be put to use in developing new products and creating new value.
MOTOBOT Ver. 1 / To "The Doctor"
Aims: Straight-line riding up to a top speed of 100 km/h; running a slalom course; cornering
Aims: Deduce the requirements for riding that exceeds human capabilities; lap a racetrack at 200 km/h or higher
Aims: Use the knowledge and underlying technologies gained from the MOTOBOT development project to deliver new value from Yamaha to our customers
What makes the MOTOBOT project unique is its approach to completely automated operation. Unlike the current methods used for automobile self-driving systems, which have progressed in recent years, the aim is for a humanoid robot to operate a vehicle unmodified for autonomous use. Based on data for vehicle speed, engine rpm, machine attitude, etc., MOTOBOT will control its six actuators* to autonomously operate the vehicle. Going forward, technology for machine position recognition (high-precision GPS, various sensors, etc.) and machine learning will be utilized to enable MOTOBOT to make its own decisions regarding the best lines to take around a racetrack and the limits of the motorcycle’s performance, so that it can improve its lap times with successive laps of the track. From this project, we will be able to visualize data about human motorcycle operation, deduce the relationship between rider input and machine behavior, and then use the resulting know-how in developing vehicles for creating even greater Kando. Also, by altering MOTOBOT’s control programming and the shapes of its operating mechanisms as necessary, we anticipate it will also be adaptable to ride other vehicles like personal watercraft and snowmobiles.
*For operating the steering, throttle, front brake, rear brake, clutch and gearshift pedal
MOTOBOT fuses Yamaha Motor's technology gained from developing motorcycles (vehicle dynamics know-how, electronic control, etc.) with technology garnered from developing our industrial robots (robot control, etc.).
The various actuators that perform riding operations are precisely controlled and can perform actions similar to a human rider.
As the project progresses, mechanism improvements, algorithm enhancement through machine learning and other factors required for high-speed track riding will make other types of high-level riding possible.