Welcome to the Qinsun Instruments Co., LTD! Set to the home page | Collect this site
The service hotline


Related Articles

Product Photo

Contact Us

Qinsun Instruments Co., LTD!
Address:NO.258 Banting Road., Jiuting Town, Songjiang District, Shanghai

Your location: Home > Related Articles > MIT’s new algorithm can train drones to relax and avoid obstacles to fly faster

MIT’s new algorithm can train drones to relax and avoid obstacles to fly faster

Author:QINSUN Released in:2024-01 Click:84

Drone competitions are a relatively new sport that typically compete on tracks with obstacles, and drones need to avoid obstacles as quickly as possible. Although drone competitions are purely for fun, the technology of avoiding obstacles in these competitions can also allow commercial drones to avoid obstacles during complex situations and time sensitive operations, such as search and rescue. The Massachusetts Institute of Technology is attempting to enable drones to fly faster while avoiding obstacles.

MIT aerospace engineers have developed an algorithm that allows drones to choose the fastest route to bypass obstacles without colliding with them. This algorithm combines simulation of drones flying over virtual obstacles and experiments involving actual drones flying the same route in the real world. When drones are trained using new algorithms, their speed of crossing obstacles can be 20% faster than drones planning flight routes using traditional algorithms.

Although the MIT team found that their algorithm can significantly accelerate the speed of flight through courses, they also found that drones trained with their new algorithm are not always faster than those trained with traditional algorithms. In professional racing, both pilots and drivers know that sometimes you have to slow down in certain areas to go faster in other areas.

The algorithm of MIT can determine that in order to travel faster on the subsequent route, even if it is surpassed by competitors, it is better to slow down. The project researchers believe that the algorithm they have developed is an important step in enabling future drones to browse highly complex environments very quickly. For example, this technology could one day be used for unmanned aerial vehicles in search and rescue operations to quickly and accurately navigate crowded and dangerous environments.

Scientists Develop Machine Tuna to Use Variable Stiffness Tails for More Efficient Swimming

According to foreign media reports, given that fish are naturally good at swimming, more and more people are imitating the body structure of fish when designing underwater robots. Scientists have now discovered that by adjusting the stiffness of their tails, these robots can swim more effectively.

In real fish, the tail muscles can harden for better high-speed sprints, or release for better low-speed cruising and maneuverability. However, robots inspired by fish must make compromises, and their tails are set to a hardness that is not ideal in all cases.

Professor Dan Quinn from the University of Virginia said, "Having a hard tail is like having a gear ratio on a bicycle. You can only be effective at one speed. It's like riding a bike with fixed gears in San Francisco; you'll be exhausted after a few blocks."

Unfortunately, it is difficult to determine when and whether fish have actually changed the hardness of their tails. Collaborating with postdoctoral researcher Zhong Qiang, Quinn turned to fluid dynamics and biomechanics to develop a theoretical model. In short, the model suggests that the tail stiffness should increase with increasing swimming speed.

In order to practically test their theory, scientists built a robot called AutoTuna called Tuna. Based on the tail stiffness model, the device utilizes a programmable tendon to automatically change the stiffness of its tail as it swims in a laboratory based canal. It is worth noting that compared to other robots with the same fixed tail stiffness, it can swim in a larger speed range and uses almost half of the energy.

Researchers are currently studying how to apply this technology to robots based on other types of swimming animals.

Quinn represents: Stiffness adjustment mechanisms like ours can be easily miniaturized, so they can support robots of various sizes and shapes. The harder part is to figure out how hard the robot should be at various swimming frequencies and speeds. We used a physical model and water channel testing to develop a control law for our robot to use when automatically adjusting its tail hardness If the robot is made larger (such as a dolphin like robot) or switched to a different swimming type (such as a ferret like robot), this model will need to be recalibrated, but this is completely achievable

The paper on this research was recently published in the journal Scientific Robotics.