In our most recent episode of Lexicon, we interviewed Doctor Xianbao Chen and Professor Gao Feng from Shanghai Jiao Tong University to discuss their groundbreaking work on a six-legged robot guide dog for the visually impaired.
Before our new episode, check out our latest merch at Interesting Engineering Shop. Engineer your style with our t-shirt mugs and discover new products! Now, let’s continue with today’s episode.
Meet our guests
Xianbao Chen is a Ph.D. graduate and a seasoned researcher in robotics. He currently works at Shanghai Jiao Tong University’s School of Mechanical Engineering. With over a decade of experience in robot design, Chen has been instrumental in developing advanced robotic systems, including the innovative six-legged robotic guide dog to assist visually impaired individuals.
His work integrates cutting-edge technologies to create practical solutions that improve daily life for those with disabilities.
Professor Gao Feng is a leading robotics and mechanical engineering expert at Shanghai Jiao Tong University. He specializes in designing and applying parallel robots and heads the research team behind the pioneering six-legged robotic guide dog project.
Under his leadership, the team has made significant strides in developing practical robotics applications, particularly assistive technologies. Professor Gao’s work is recognized for its potential to revolutionize accessibility and independence for visually impaired people worldwide.
The world is ready for robot guide dogs
As Chen explained to IE, the main inspiration behind the robotic guide dog is their lack in his home nation of China. Amazingly, despite there being over 17 million people in China who are visually impaired, fewer than 400 trained guide dogs are available to assist them. “We saw a huge demand for guide dogs in China, with over 17 million visually impaired people and less than 400 guide dogs available. This inspired us to develop the Hexapod robot to fill this gap,” Chen explained.
While invaluable, traditional living guide dogs take a long time to train and can be relatively expensive. In fact, each guide dog costs around $30,000 to train.
But even after training, not all dogs are found to be suitable for this role, further limiting their availability. Moreover, the concept of guide dogs is relatively new in China, where cultural and regulatory barriers also restrict their widespread adoption.
To this end, the Shanghai Jiao Tong University team decided to explore the development of a mass-produced robotic alternative. This would help reduce costs and increase the accessibility of guide dog technology for those in need. “By consolidating the supply chain and moving towards mass production, we are working to significantly reduce the cost of the robot, making it more accessible to those who need it,” Professor Gao Feng explained.
Under the robot dog’s hood
The robotic guide dog Professor Gao and his team developed is no ordinary robot. Unlike traditional four-legged robots, this guide dog features a six-legged design, which offers enhanced stability and mobility across various terrains.
TThe robot’s hexapod design helps it maintain balance even when traversing uneven surfaces. Given its intended role, this is a critical feature for assisting visually impaired users.
“The answer is quite simple,” said Gao Feng. “A six-leg robot is more stable. When it walks, three legs always remain on the ground, forming a triangle, which is inherently more stable than a quadruped robot that walks on two legs at a time.” As Chen explained to us, this stability is crucial for the robot’s ability to navigate complex environments, such as city streets with obstacles, stairs, and other potential hazards. But it doesn’t end there.
A battery of sensors
The robot guide dog is also equipped with a sophisticated array of sensors, including visual, auditory, and force sensors, that allow it to “see,” “hear,” and “feel” its surroundings. These sensors work together to create a comprehensive map of the environment, enabling the robot to guide its user safely and effectively.
“Our robot can identify traffic lights using cameras and machine learning, something traditional guide dogs cannot do. This feature is crucial for ensuring the safety and independence of visually impaired users,” Gao Feng noted.
In addition to its navigational capabilities, the robot features advanced voice recognition technology. According to Chen, the system can understand commands with over 90% accuracy and respond in less than one second. However, at present, this is primarily in Chinese.
“The challenge is that the user will not always speak commands as expected. Sometimes, they speak casually, so the system may not always understand. We are improving this aspect to make the robot more user-friendly,” Chen explained to IE.
How the robo-guide dog performs
All well and good, but for the robot guide dog to have any future, it really needs to be road-tested with bona fide visually impaired users. To this end, the team has conducted field tests with visually impaired individuals, gathering feedback to refine the robot’s design and functionality.
A married couple, Li Fei and Zhu Sibin participated in these tests and provided valuable insights that have helped shape the robot’s development. “They agree with the method that the robot navigates automatically to take them to where they want to go,” Chen explained.
“However, they also had some suggestions. For example, they think the robot can currently recognize very few commands. In the future, they hope there can be more commands available, and they also suggested that the robot should broadcast more frequently, such as providing updates on the surroundings or offering advice,” he added.
Another feedback area focused on the tactile interface between the user and the robot. Currently, the robot is controlled via a stick that connects the user to the device, allowing them to push or pull the robot as needed.
The users expressed a desire for greater sensitivity in this control mechanism, which the team is working to address in future iterations. “The feedback from users is invaluable,” said Gao Feng. “It helps us refine the robot to better meet their needs and ensure it enhances their independence and safety.”
Looking into the future
While the robotic guide dog offers numerous advantages, it also raises important ethical considerations, particularly regarding its potential impact on traditional guide dogs and the human-animal bond. Professor Gao Feng acknowledged these concerns, emphasizing that the goal is not to replace traditional guide dogs but to complement them.
“We believe that the robotic guide dogs and traditional guide dogs can coexist,” Gao said. “The emotional companionship of traditional guide dogs cannot be replaced by robotic guide dogs. However, for those who do not have access to a traditional guide dog, a robotic alternative can provide significant benefits,” he added.
Looking to the future, the team is focused on further improving the robot’s performance, including enhancing its ability to recognize and avoid obstacles, understand casual speech, and even potentially incorporate features like GPS tracking or integration with platforms like large language models (LLMs) for more dynamic user interaction.
RECOMMENDED ARTICLES
Gao Feng also sees potential for global applications of this technology, noting that the shortage of guide dogs is a worldwide issue, not just a problem in China. “This technology has global potential because the shortage of guide dogs is not just a problem in China; it’s an issue worldwide. We plan to adapt the robot to different cultural and environmental contexts.”
0COMMENT
NEWSLETTER
The Blueprint Daily
Stay up-to-date on engineering, tech, space, and science news with The Blueprint.
Christopher McFadden Christopher graduated from Cardiff University in 2004 with a Masters Degree in Geology. Since then, he has worked exclusively within the Built Environment, Occupational Health and Safety and Environmental Consultancy industries. He is a qualified and accredited Energy Consultant, Green Deal Assessor and Practitioner member of IEMA. Chris’s main interests range from Science and Engineering, Military and Ancient History to Politics and Philosophy.
0