Researchers at Arizona State University are developing robotic dogs equipped with artificial intelligence to help in hazardous environments and support people with disabilities. The project, led by Ransalu Senanayake, assistant professor of computer science and engineering in the School of Computing and Augmented Intelligence at ASU, focuses on using advanced robotics for real-world applications.
Senanayake’s team works with the Unitree Go2, a quadrupedal robot fitted with AI cameras, LiDAR, and a voice interface. The robot is being trained to perform tasks such as search-and-rescue operations and guiding visually impaired individuals through complex spaces.
“We’re not just writing code for robots,” Senanayake said. “We’re creating tools to solve problems that matter, like saving lives in dangerous environments and making the world more accessible.”
The Laboratory for Learning Evaluation and Naturalization of Systems (LENS Lab), founded by Senanayake, is pushing robotics forward by integrating AI models that allow robots to understand and adapt to their surroundings.
“AI breakthroughs are finally turning robots into a feasible, ubiquitous reality,” Senanayake said. “We are teaching our robots to see, hear and move in complex environments, making them useful in a variety of situations.”
Eren Sadıkoğlu, a master’s student in robotics and autonomous systems at ASU, is developing vision- and language-guided navigation tools for the robotic dog. His work uses reinforcement learning so the robot can move safely through disaster zones after events like earthquakes.
“The robots need to jump over obstacles, duck under things and do some acrobatic movements,” Sadıkoğlu said. “It’s not just about moving from point A to point B. It’s about moving safely and strategically through difficult terrain.”
Thanks to sensors such as RGB-depth cameras and touch sensors on its feet, the robot can adapt to unpredictable conditions found in disaster areas.
“This research is about making robots that can go where humans can’t, keeping rescue teams safe while saving lives,” Sadıkoğlu said.
Undergraduate student Riana Chatterjee is working on algorithms that will enable the robotic dog to assist visually impaired people by guiding them indoors or outdoors.
“My project is about combining deep learning technologies to enable the robot to understand its surroundings and communicate that to a visually impaired person,” Chatterjee said.
Chatterjee uses computer vision models like YOLO for object recognition as well as transformer-based monocular depth estimation so the robot can gauge distances. Vision language models allow it to describe what it sees or offer guidance verbally.
“For me, robotics is about making life easier for people with impairments. It’s fascinating to think about how AI can change the lives of those who need it the most,” she said.
Senanayake sees broader potential for robotics: “The future of robotics is exciting, and I hope that with our research, we’ll be able to bring these technologies into the homes and communities that need them most.”
Ross Maciejewski, director of ASU’s School of Computing and Augmented Intelligence, emphasized preparing students for technological changes: “Our goal is to equip students with both the theoretical foundations and practical skills needed to tackle the challenges of tomorrow,” he said. “By blending AI with robotics, we are not only expanding the capabilities of technology but also creating future leaders who will bring transformative solutions to critical issues.”
ASU has been recognized nationally for its innovation efforts; it was named number one in innovation for eight consecutive years by U.S. News & World Report according to university news.
In addition to these projects at ASU’s LENS Lab, other university-related technology initiatives include partnerships between ASU tech startups such as Argos Vision—which develops smart traffic cameras—and local government agencies like Phoenix’s Street Transportation Department as described in a city press release.
