- Robot system designed to climb stairs and handle a variety of environments can be useful in search-and-rescue operations.
- The system depends on vision inputs to decide its path just like humans and animals.
Quadrupedal robots are considered to offer better stability over bipedal robots. At slow speeds, a quadrupedal robot may move only one leg at a time, ensuring a stable tripod. “Empowering small robots to climb stairs and handle a variety of environments is crucial to developing robots that will be useful in people’s homes as well as search-and-rescue operations,” said Deepak Pathak, an assistant professor in the Robotics Institute.
Researchers at Carnegie Mellon University’s School of Computer Science and the University of California, Berkeley, have designed a robotic system that enables a low-cost and relatively small legged robot to climb and descend stairs nearly its height; traverse rocky, slippery, uneven, steep and varied terrain; walk across gaps; scale rocks and curbs; and even operate in the dark.
The team tested the robot on uneven stairs and hillsides at public parks, challenging it to walk across stepping stones and over slippery surfaces. The robot adapts quickly and masters challenging terrain with the help of its vision and a small onboard computer. It is trained with 4,000 clones of it in a simulator. The motor skills learned by the robot from the simulator was recorded in neural networks. This neural network was uploaded to the physical robot.
The system depends on the vision inputs to control the robot. This technique allows the robot to react to oncoming terrain quickly and move through it effectively. “This system uses vision and feedback from the body directly as input to output commands to the robot’s motors,” said Ananye Agarwal, an SCS Ph.D. student in machine learning. “This technique allows the system to be very robust in the real world. If it slips on the stairs, it can recover. It can go into unknown environments and adapt.”
The robot motion is derived from the way human hips work. When a human has to lift its leg up high to scale a ledge or hurdle, it uses its hips to move its leg out to the side, called abduction and adduction. This robot system hip abduction to tackle obstacles that trip up some of the most advanced legged robotic systems on the market.
The system’s onboard memory enables the rear legs to remember what the camera at the front saw and maneuver to avoid obstacles. This research could lead toward solving existing challenges facing legged robots and bringing them into people’s homes.