AI bike developed in China self-balances, avoids obstacles and responds to voice commands 

If you struggle to cycle, scientists may have the answer! AI bike developed in China self-balances, avoids obstacles and responds to voice commands

  • Tsinghua University researchers used small AI chip mounted on the back wheel 
  • Microphone picks up voice commands and speed sensor detects momentum
  • Breakthrough comes three years after a spoof April Fool’s video from Google

We already have driverless cars, but scientists have now created a self-cycling bicycle.

Perfect for the wobbly rider, the bike keeps itself upright, spots speed bumps and automatically swerves around obstacles.

The bicycle is powered by artificial intelligence, so just like voice-operated assistant Alexa, responds to commands to speed up, slow down and turn left or right. 

It was created by researchers at Tsinghua University in Beijing, using a small AI chip mounted on the back wheel.

The breakthrough comes three years after a spoof April Fool’s video from Google which suggested the firm had created a self-riding bike, but revealed in a ‘making of’ video that it had been faked.

In action: Footage of the bike shows it navigating a running track without a cyclist at the helm – instead, it follows commands and responds to stimuli

AI: The bicycle is powered by artificial intelligence, so just like voice-operated assistant Alexa, responds to commands to speed up, slow down and turn left or right

AI: The bicycle is powered by artificial intelligence, so just like voice-operated assistant Alexa, responds to commands to speed up, slow down and turn left or right

HOW DOES IT WORK? 

The bike was created by researchers at Tsinghua University using a small  cross-paradigm neuromorphic chip called Tianjic, which is mounted on the back wheel. 

A gyroscope is used to measure the bicycle’s stability to keep it upright, while a camera detects obstacles in its path. 

A microphone then picks up voice commands from the rider and a speed sensor detects how fast it is going. 

Experts say the technology behind the bike, which also has the ability to perform S-curves and high-speed turns, acts similarly to the human brain in spotting obstacles and responding to them.

But it also uses machine-learning algorithms, making every bike function possible to control from a single chip.

The Chinese researchers use a gyroscope to measure the bicycle’s stability to keep it upright and a camera to detect obstacles in its path. 

A microphone picks up voice commands from the rider and a speed sensor detects how fast it is going.

Professor Will Stewart, chairman of the Communications Policy Panel at the Institution of Engineering and Technology, who was not involved in the study, said: ‘This is a fascinating example of a multi-purpose programmable AI chip, cleverly demonstrating the many functions needed to operate a bicycle.

‘It is controlling the balance, understanding what is in front of the bicycle, and steering too.

‘It is a step forward in making AI that much more useful for our everyday lives.’ 

A study on the bicycle, published in the journal Nature, show it is perfect for cross-country bicycle rides, being able to track a person in front and follow them in a straight line.’

Obstacle avoidance: Experts say the technology behind the bike, which also has the ability to perform S-curves and high-speed turns, acts similarly to the human brain in spotting obstacles

Obstacle avoidance: Experts say the technology behind the bike, which also has the ability to perform S-curves and high-speed turns, acts similarly to the human brain in spotting obstacles

Study: Analysis on the bicycle, published in the journal Nature, show it is perfect for cross-country bicycle rides, being able to track a person in front and follow them in a straight line

Study: Analysis on the bicycle, published in the journal Nature, show it is perfect for cross-country bicycle rides, being able to track a person in front and follow them in a straight line

In a video on YouTube, it can be seen cycling over a speed bump and avoiding traffic cones, without a rider operating the pedals.

A researcher walking beside the bike simply orders it to speed up, go left or cycle in a straight line, which it does using its audio sensor and motor.

Nick Chamberlin, policy manager at British Cycling, said: ‘We are very interested to see what benefits AI technology might have to help more people enjoy the benefits of bike riding, especially the elderly and people living with life-limiting illness or disability.

‘New technology means that for the first time in a generation the future of mobility is exciting.

‘There are many questions still about the safety of all autonomous vehicles but as we learn more we can understand the positive benefits and work with society and policy makers to make sure that those benefits are realised.’ 

Experts say the technology behind the bike, which also has the ability to perform S-curves and high-speed turns, acts similarly to the human brain in spotting obstacles and responding to them.

But it also uses machine-learning algorithms, making every function of a bike possible to control from a single chip.    

Details of the research was published in the journal Nature. 

Read more at DailyMail.co.uk