麻豆村

When Leo Wang arrived at 麻豆村 from Hong Kong, he was already fascinated by robots. But it wasn鈥檛 until he joined the Robomechanics Lab led by聽 that his interest evolved into a mission: to teach quadrupedal robots to climb steep terrain using reinforcement learning.

鈥淚鈥檝e always dreamed of building general-purpose robots that could help in the home or navigate complex environments,鈥� said Wang, now a sophomore in electrical and computer engineering. 鈥淩einforcement learning felt intuitive, like how babies learn to walk through trial and error.鈥�

础听Summer Undergraduate Research Fellowship(opens in new window) (SURF) enabled Wang to begin training a robotic dog to climb simulated slopes as steep as 45 degrees. So far, his model has reached 36 degrees, and he鈥檚 optimistic about pushing further.

鈥淭here鈥檚 no hard-coded algorithm telling the robot how to move. It learns by itself, which is incredible to watch,鈥� he said.

To achieve his goal, Wang built a custom simulation environment where the robot learns by trial and error. Each successful step earns a reward; each stumble is penalized. The process demands immense computing power, which the lab provides through access to high-performance machines.

鈥淩einforcement learning is computationally intensive,鈥� Wang explained. 鈥淵ou need supercomputers to run thousands of iterations faster than real time.鈥�

The challenge, he said, was designing the right rewards to motivate the robotic dog to climb properly and not exploit the simulator.

鈥淚 didn鈥檛 realize how hard it would be to build a realistic training environment. If the simulation isn鈥檛 accurate, the robot might learn behaviors that don鈥檛 transfer to the real world. Even small glitches can be exploited by the algorithm. For example, if he rewarded the robot dog according to its elevation from the ground, the robot might simply jump as high as possible and not learn to climb the hill in front of it at all. Thus, a better reward system would be one that gives higher rewards as the robot gets closer to the top of the hill,鈥� he said.

Wang鈥檚 work is more than academic. He envisions real-world applications in search-and-rescue missions and environmental monitoring. Inspired by the agility of mountain goats, he hopes future robots will be able to traverse rugged terrain, identify footholds and operate autonomously in dangerous or remote areas.

鈥淩obots can go where humans can鈥檛. They can provide valuable help fighting forest fires, rescuing lost hikers or monitoring ecosystems from inaccessible cliffs,鈥� he said.

His journey into reinforcement learning also reshaped his academic path. Initially focused on mechanical engineering, Wang switched majors after the fellowship gave him the chance to explore software and artificial intelligence.

鈥淚 spent a lot of time in high school building robots, but I hadn鈥檛 coded much. SURF opened the door to a whole new side of robotics for me,鈥� he said.

Working in Johnson鈥檚 lab has been a source of immense fulfillment and inspiration for Wang.

鈥淚t鈥檚 an amazing feeling to be surrounded by people who share your passion,鈥� he said. 鈥淲e have weekly lab lunches and social events through which I learned so much from talking with Ph.D. students about their research and grad school experiences. I could see myself following a similar path.鈥�

As for advice to students who are still thinking about applying for the fellowship, he said he would tell them to 鈥済o for it.鈥�

鈥淚t鈥檚 a rare opportunity to dive deep into research and discover what you truly enjoy,鈥� he said.聽