When developing robotic systems and computing tools, computer scientists are often inspired by animals or other biological systems. In fact, depending on the characteristics and unique purpose of a system, nature usually provides specific examples of how it could achieve its goals quickly and efficiently.
Researchers at Shanghai Jiaotong University have recently developed a new bio-inspired and computer-based obstacle avoidance system that could improve the navigation of flying robots operating in dynamic environments. This system, presented in a paper on arXiv , is inspired by the way owls detect and avoid objects or other animals in their surroundings.
“Although owls are not able to move their eyes in any direction, they have a very flexible neck, which can rotate up to 270 degrees, which allows them to observe quickly even in the back without moving their torso.” , the researchers write in their paper.
What the system does
To replicate the way owls move their eyes in different directions and detect both static and moving objects around them, the researchers mounted a servomotor and a stereo camera on a quadrotor (ie an unmanned flying robot with four rotors).
In their design, the servomotor acts as a neck, and the stereo camera as a head. Due to the light weight of the stereo camera, it can move much faster than the robot’s body, and its movements do not affect the quality of the robot’s movements or the direction in which it flies.
The system uses a sensor scheduling algorithm to estimate how much the robot would benefit from detecting objects in different directions, and plans the angle at which its “head” (stereo camera) should rotate.
So, the unmanned flying robot continuously and actively senses its surroundings, identifying obstacles that prevent it from moving quickly.
In addition, the system tracks and predicts the trajectories of moving obstacles in its vicinity, adapting its movements to changes in the environment. Finally, based on the data collected by the stereo camera, the system uses a sampling-based route planner to plan a collision-free route. This highlights the movements that would allow the robot to reach a certain location or complete a mission without colliding with other objects.
This system could also reproduce the behavior of other animals in the future
“Overall, this system is called an active sense and avoidance system (ASAA),” the researchers explain in their paper. “As far as we know, this is the first system that applies active stereo vision to achieve obstacle avoidance for flying robots.”
Researchers at Shanghai Jiaotong University evaluated their ASAAA system in a series of experiments performed in real environments. In these experiments, a quadrotor either had to get to the desired location avoiding all obstacles in its path, or it had to monitor and catch an artificial rat. The results of these tests are promising, as the robot performed well on both tasks, quickly adapting to sudden changes in its environment and avoiding collisions with both static and moving obstacles.
Moreover, the prototype manufactured by the researchers uses a single stereo camera. So, it is relatively inexpensive. This can make large-scale manufacturing and implementation easier.
In the future, this system could be used to carry out missions in a wide range of environments, from urban areas to natural environments populated mostly by wild animals.
The system could also inspire the development of other flying robots with improved obstacle avoidance capabilities based on similar models. In the following studies, researchers will try to create systems that reproduce the behavior of other animals , while using machine learning techniques, to further improve the detection performance of their system.