Huihuan Qian

Ziran Zhang, Yiwei Lyu, Fahad Raza et al.

Sailing robots provide a low-cost solution to conduct the ocean missions such as marine exploration, pollution detection, and border surveillance, etc. However, compared with other propeller-driven surface vessels, sailboat suffers in complex marine wind field due to its low mobility. Especially in tacking, sailboats are required to head upwind, and need to make a zig-zag path. In this trajectory, a series of turnings, which will cross the challenging no-go zone, place significant challenge as it will reduce speed greatly and consequently result in unsuccessful turning. This paper presents a hybrid sailboat design to solve this issue. Electric propellers and control system are added to a model sailboat. We have further designed the control strategy and tuned the parameters (PWM-time) experimentally. Finally, the system and control can complete the tacking maneuver with average speed approximately 10% higher and enhanced success rate, though the sailboat weight is much heavier.

Ziran Zhang, Zixuan Yao, Qinbo Sun et al.

Autonomous Surface Vehicles (ASVs) provide an effective way to actualize applications such as environment monitoring, search and rescue, and scientific researches. However, the conventional ASVs depends overly on the stored energy. Hybrid Sailboat, mainly powered by the wind, can solve this problem by using an auxiliary propulsion system. The electric energy cost of Hybrid Sailboat needs to be optimized to achieve the ocean automatic cruise mission. Based on adjusted setting on sails and rudders, this paper seeks the optimal trajectory for autonomic cruising to reduce the energy cost by changing the heading angle of sailing upwind. The experiment results validate the heading angle accounts for energy cost and the trajectory with the best heading angle saves up to 23.7% than other conditions. Furthermore, the energy-time line can be used to predict the energy cost for long-time sailing.

Junqing Qiu, Guoren Zhong, Yihua Lu et al.

We introduce a neural network (NN) strictly governed by Newton's Law, with the nature required basis functions derived from the fundamental classic mechanics. Then, by classifying the training model as a quick procedure of 'force pattern' recognition, we developed the Newton physics-based NS scheme. Once the force pattern is confirmed, the neuro network simply does the checking of the 'pattern stability' instead of the continuous fitting by computational resource consuming big data-driven processing. In the given physics's law system, once the field is confirmed, the mathematics bases for the force field description actually are not diverged but denumerable, which can save the function representations from the exhaustible available mathematics bases. In this work, we endorsed Newton's Law into the deep learning technology and proposed Newton Scheme (NS). Under NS, the user first identifies the path pattern, like the constant acceleration movement.The object recognition technology first loads mass information, then, the NS finds the matched physical pattern and describe and predict the trajectory of the movements with nearly zero error. We compare the major contribution of this NS with the TCN, GRU and other physics inspired 'FIND-PDE' methods to demonstrate fundamental and extended applications of how the NS works for the free-falling, pendulum and curve soccer balls.The NS methodology provides more opportunity for the future deep learning advances.

Wenhao Ding, Shuaijun Li, Huihuan Qian

In this paper, we propose a navigation algorithm oriented to multi-agent environment. This algorithm is expressed as a hierarchical framework that contains a Hidden Markov Model (HMM) and a Deep Reinforcement Learning (DRL) structure. For simplification, we term our method Hierarchical Navigation Reinforcement Network (HNRN). In high- level architecture, we train an HMM to evaluate the agent's perception to obtain a score. According to this score, adaptive control action will be chosen. While in low-level architecture, two sub-systems are introduced, one is a differential target- driven system, which aims at heading to the target; the other is a collision avoidance DRL system, which is used for avoiding dynamic obstacles. The advantage of this hierarchical structure is decoupling the target-driven and collision avoidance tasks, leading to a faster and more stable model to be trained. The experiments indicate that our algorithm has higher learning efficiency and rate of success than traditional Velocity Obstacle (VO) algorithms or hybrid DRL method.

Shuaijun Li, Yu Meng, Wei Li et al.

Monocular camera systems are prevailing in intelligent transportation systems, but by far they have rarely been used for dimensional purposes such as to accurately estimate the localization information of a vehicle. In this paper, we show that this capability can be realized. By integrating a series of advanced computer vision techniques including foreground extraction, edge and line detection, etc., and by utilizing deep learning networks for fine-grained vehicle model classification, we developed an algorithm which can estimate vehicles location (position, orientation and boundaries) within the environment down to 3.79 percent position accuracy and 2.5 degrees orientation accuracy. With this enhancement, current massive surveillance camera systems can potentially play the role of e-traffic police and trigger many new intelligent transportation applications, for example, to guide vehicles for parking or even for autonomous driving.

Wenhao Ding, Shuaijun Li, Guilin Zhang et al.

In this paper, we present an accurate approach to estimate vehicles' pose and shape from off-board multiview images. The images are taken by monocular cameras and have small overlaps. We utilize state-of-the-art convolutional neural networks (CNNs) to extract vehicles' semantic keypoints and introduce a Cross Projection Optimization (CPO) method to estimate the 3D pose. During the iterative CPO process, an adaptive shape adjustment method named Hierarchical Wireframe Constraint (HWC) is implemented to estimate the shape. Our approach is evaluated under both simulated and real-world scenes for performance verification. It's shown that our algorithm outperforms other existing monocular and stereo methods for vehicles' pose and shape estimation. This approach provides a new and robust solution for off-board visual vehicle localization and tracking, which can be applied to massive surveillance camera networks for intelligent transportation.