The progress made so far in the design of legged robots has been mostly in the areas of leg coordination, gait control, stability, incorporation of various types of sensors, etc. This progress has resulted in the demonstration of rudimentary robotic walking capabilities in various labs around the world. The more stable of these robots have multiple legs, four or more, and some can even climb stairs. But what is missing in most of these robots is some perception-based high-level control that would permit a robot to operate with a measure of autonomy. Equipping a robot with perception-based control is not merely a matter of adding to the robot yet another module; the high-level control must be tightly integrated with the low-level control needed for locomotion and stability.

 

So far in our project, we have implemented a model-based method for recognizing a staircase using a 2D image of a 3D scene containing the staircase. The staircase recognition is achieved by obtaining the pose of the camera coordinate frame that aligns the model edges with the image edges. The method contains the matching, the pose estimation, and refinement procedures. The computational complexity of matching is ameliorated by grouping together edges with certain common geometric characteristics. The refinement process uses all matched features to tightly fit the model edges with camera image edges. The resulting recognition is used to guide the robot to climb stairs.

 

 

 

 

 

    •    Daniel Pack