AI-Enabled Tactical Route Planning
To simulate the real-world drone tracking and path planning process, I use air-sim together with Unreal Engine to simulate the car tracking process. Firstly, we built a true-to-real-world environment in Unreal Engine (UE4), as shown in the first picture, which reduced the cost to do the real physical experiments. Then I implement a deep-learning-based depth-map algorithm (Monodepth2) and segmentation algorithm(Detectron2) in the virtual environment. These two methods will generate the 3D occlusion identification and map it into the Unreal Engine virtual environment. Furthermore, we used RRT algorithms for the 2d path planning (Fig 2). We set the starting point (X) and a target point (O). The red line is the optimal path and the green line is all possible paths (Fig 3). After getting the optimal path from above, we change the path into spline in UE4. The planned path in Fig 3 is executed by the virtual agent in Fig 4. In the last step, we designed a spline-based autonomous moving method for agents using a blueprint that also could record real-time position data in TXT format. The recorded position data will be used for the drone to track. This technology can be used for future autonomous driving as drones can assist the car in driving and path planning.
Human-Robot Collaboration System (LMCO project) for Target Tracking
First of all, I use YOLO for target detection (Fig 1). The target data will be stored in the database first. I predefined multiple positions of virtual human targets as shown in Fig 2. I also put several fixed-camera in the environment which provides views for human operators. When drones find the target, they will track the target (Fig 3 – 4) using a Neural Network based trajectory prediction algorithm. When drones lost targets due to bad weather or obstacles (Fig 5), the drone can receive messages from the human operator (Fig 6) through the fixed-camera windows, which assists the path planning for the drone. Drones will update the path based on the click position. I also designed a fog system in the environment which means we can simulate the drone’s tracking ability in different densities of fog.
Research on Volumetric Contact Theory to Electrical Contact between Random Rough Surfaces
The core problem of metal contact was to calculate the contact area accurately. Traditionally, researchers tend to use fractal theories, while the applications are limited in some cases. Inspired by holes in sponges, I used the concept of porosity to develop a universal methodology. The big picture was to divide the volume of the metal by the height of the refactored surface. With the reconstructed surface, I wrote a program to iterate the height of the cylinder mentioned above recursively. Consequently, the real contact area can be calculated. Luckily, my supervisor, Professor Wurui Ta, got contact with Dr. BNJ Persson – who raised Persson’s contact theory, which becomes one of the most important theories in contact mechanics – to evaluate the model I developed. Combining with Persson’s method, we also propose a new resistance calculating method which could be used to determine superconducting cables’ resistance quicker and cheaper. The simulation results show better accuracy and speed than any existing method. This research was published in Tribology International https://doi.org/10.1016/j.triboint.2021.107007
Numerical Calculations of Ellipsoid Sand’s Movement Considering Magnus Force
In nature, the sand storm will be very hard to simulate. My undergraduate school is near the desert which suffers from sand storms from time to time. My dean, Professor Zhou, and his wife, Professor Zheng, devoted all their lives to studying the sandstorm movement and its control. I respect their work and extended the application scope of the spherical sand movement model developed by Professor Zheng to ellipsoid. I began by assuming the sand particles as all spherical and calculated the trajectory accordingly using the Fourth Order Runge-Kuta algorithm. I then utilized the Monte Carlo algorithm to expand the ideal spheres to a more general case – ellipses – taking Magnus force into consideration. After numerous tests, one of the conclusions raised my attention: under a certain geometrical condition, the moving trajectory of ellipsoidal and spherical shapes are nearly identical. Ideally, this finding can reduce the calculation by 67% and provide potential development for other sandstorm movement models.
Mechanical Simulation of Flexible Optics Devices
I am proficient in operating finite-element analysis software, such as COMSOL, ABAQUS, ANSYS, etc. 2020’s summer, I have conducted post-buckling analysis for three-layer structure (PI, Silicone, and SU8) at Westlake University, and attempted to measure cell elastic modulus by optical methods and got the deformation of cells indirectly through the changes of optical properties of elastic substrates. (The above pictures are the post-buckling analyses of octopus structure) Further, I verified the experimental data by means of finite element analysis software ABAQUS and COMSOL to prove their reliability, even though the former one has better operation speed and convergence.
Research on Aquatic Unmanned Aerial Vehicles
After reading more than 200 scientific articles, I analyzed the former designs on aquatic unmanned aerial vehicles and raised a feasible conceptual proposal based on fish imitation which doesn’t dive into the water. This new design can be operated underwater more effectively underwater because of the suitable shape for underwater running.
Research on the Residual Stress of Superconducting Bucks YBCO Based on Drilling Method
The most popular way researchers now used to measure residual stress of superconducting bucks (YBCO) is using x-ray which is very expensive. Another cheaper way is to use the drill method which is not suitable for YBCO bucks which are very fragile. After careful inspection of traditional Chinese hand-drills, we found that the drill can be adapted to measure the residual stress as the drilling frequency can be adjusted. After modeling and building, we make a prototype drill that can be used to measure the residual stress. The experimental results are very close to the values measured by expensive equipment. This research was published on Acta Mechanica Solida Sinica https://doi.org/10.1007/s10338-020-00192-x
Immune Cell’s Mechanical Properties Based on AFM
Cancer has been bothering humans for a long time. To find cancer symptoms as early as possible is very important. The current methods can not identify early-stage cancer effectively. As a consequence, my group tries to identify early-stage cancer from a mechanical perspective. Immune cells and cancer cells have different mechanical properties, using AFM we can tell the difference between these cells. If we are given a potential cancer patient, we can measure the cells in his blood to find if there are any cancer cells. In the future, we can even make a portable device that can measure the cell status in time. If the device finds potential cancer cells, then the patient can go to the hospital for further examination.
