New AI platform to design hybrid UAV that operates using a single controller

Unmanned aerial vehicles (UAV) better known as drones combines the advantages of both multi-copters and fixed-wing planes. Multi-copters are popular for their flight flexibility and stable hovering capabilities. Fixed-wing airplanes, on the other hand, are more energy-efficient during level flight, making them better vehicles for long-distance flight.

However, hybrid UAVs are rarely used because controller design is challenging due to its complex, mixed dynamics.

A team from MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) has designed a new AI simulation platform that lets users create their own hybrid, fixed-wing drones. The user can develop drones of different sizes and shapes that can switch between hovering and gliding – all by using a single controller.

The platform simplifies the customization and design process for any hybrid drones. “Our method allows non-experts to design a model, wait a few hours to compute its controller, and walk away with a customized, ready-to-fly drone,” says MIT CSAIL grad student Jie Xu. “The hope is that a platform like this could make more these more versatile ‘hybrid drones’ much more accessible to everyone.

We propose a computational approach to automatically design a mode-free, model-agnostic neural network controller for customized hybrid UAVs (left). Our novel reinforcement learning framework enables the training of a controller in a stochastically enhanced physics simulator (right bottom) and the crossing of the gap between simulation and reality (right top).
We propose a computational approach to automatically design a mode-free, model-agnostic neural network controller for customized hybrid UAVs (left). Our novel reinforcement learning framework enables the training of a controller in a stochastically enhanced physics simulator (right bottom) and the crossing of the gap between simulation and reality (right-top).

In typical designs, drone experts need to design separate controllers for the helicopter flight mode, the plane flight mode and a “transition mode” that lets pilots switch between the two. As a result, the system often needs to be designed manually and from scratch for every drone, which can be a difficult, expensive, and time-consuming process.

For skipping this hassle of manually building three modes, researchers have turned to the neural networks to compute a controller automatically. Teaching a machine about how to fly is difficult. Most methods are tested in simulation but not on real hardware, which often leads to an unexpected interruption.

Whereas, the researchers’ new neural-based controller design trained by reinforcement learning techniques. In this system, users first design the geometry of a hybrid UAV by selecting and matching parts from a provided data set. The design is then used in a realistic simulator to compute and test the UAV’s flight performance automatically.

The algorithm is then applied to automatically learn a controller for the UAV to achieve the best performance in the high-fidelity simulation. The team successfully verified their method both in simulation and real flight trials.

In this research, the team delivers a novel model-agnostic method to automate the design of controllers for vehicles with vastly different configurations.

In future work, the team is planning to investigate how to increase the maneuverability through improved geometry design. This will help perfect the flight performance of the UAV.

The team will present their novel computational controller design at SIGGRAPH 2019, held 28 July-1 August in Los Angeles.

Also Read

Recent Articles

Turning plastic water bottles into affordable prosthetic limbs

Most currently available prosthetic limbs tend to be lacking in functionality or are unaffordable to many who need them. Alongside this need for prosthetic...

Langogo, AI-powered pocket translator that speaks 70 languages

Every outdoor adventure lover might have faced language barriers while traveling. At some point, we were unable to understand anything said to us in...

Mercedes-Benz revealed A-Class and B-Class plug-in hybrids for Europe

Like most other automakers, Mercedes-Benz is also on the mission to electrify its lineup of vehicles in the near future. Now it is adding...

The redesigned Ocean Cleanup device is ready to remove the ocean plastic

With each passing year, we expose the ocean to more pollutants, from trash to chemicals. This wide range of pollution endangers marine ecosystems. Fortunately,...

Aston Martin’s latest mid-engined sportscar has taken its first flight

On Friday, Aston Martin has given the world the first glimpse of its latest mid-engined Valhalla hypercar on the track alongside its sibling Aston...

Stay on top - Get the daily news in your inbox

Related Stories