A Consistent Round-Up Strategy Based on PPO Path Optimization for the Leader-Follower Tracking Problem.

Single UAVs have limited capabilities for complex missions, so suitable solutions are needed to improve the mission success rate, as well as the UAVs' survivability. A cooperative multi-UAV formation offers great advantages in this regard; however, for large and complex systems, the traditional control methods will be invalid when faced with unstable and changing environments. To deal with the poor self-adaptability and high requirements for the environmental state information of traditional control methods for a multi-UAV cluster, this paper proposes a consistent round-up strategy based on PPO path optimization to track targets. In this strategy, the leader is trained using PPO for obstacle avoidance and target tracking, while the followers are expected to establish a communication network with the leader to obtain environmental information. In this way, the tracking control law can be designed, based on the consistency protocol and the Apollonian circle, to realize the round-up of the target and obstacle avoidance. The experimental results show that the proposed strategy can achieve the round-up of the target UAV and guide the pursuing multi-UAV group to avoid obstacles in the absence of the initial detection of the target. In multiple simulated scenarios, the success rates of the pursuit multi-UAV cluster for rounding up the target are maintained above 80%.

A planar tracking strategy based on multiple-interpretable improved PPO algorithm with few-shot technique.

Facing to a planar tracking problem, a multiple-interpretable improved Proximal Policy Optimization (PPO) algorithm with few-shot technique is proposed, namely F-GBQ-PPO. Compared with the normal PPO, the main improvements of F-GBQ-PPO are to increase the interpretability, and reduce the consumption for real interaction samples. Considering to increase incomprehensibility of a tracking policy, three levels of interpretabilities has been studied, including the perceptual, logical and mathematical interpretabilities. Detailly speaking, it is realized through introducing a guided policy based on Apollonius circle, a hybrid exploration policy based on biological motions, and the update of external parameters based on quantum genetic algorithm. Besides, to deal with the potential lack of real interaction samples in real applications, a few-shot technique is contained in the algorithm, which mainly generate fake samples through a multi-dimension Gaussian process. By mixing fake samples with real ones in a certain proportion, the demand for real samples can be reduced.

Resolution improvement of dipole source localization for artificial lateral lines based on multiple signal classification.

The lateral line is a critical mechanosensory organ that enables fish to perceive the surroundings accurately and rapidly. Massive efforts have been made to build an artificial lateral line system rivaling that of fish for underwater vehicles. Dipole source localization has become a standard problem for evaluating the sensing capabilities of the developed systems. In this paper we propose, for the first time, the multiple signal classification (MUSIC) method in order to achieve high-resolution dipole source localization based on spatial spectrum estimation. We also present the minimum variance distortionless response (MVDR) by making an improvement to the previous Capon's method. Experiments are conducted on a linear prototype of lateral line canal and the localization performance of these two methods are compared. The results show that the MUSIC method provides an overall localization resolution improvement of 10.4% and maintains a similar level of localization accuracy compared with the MVDR method. Further studies show that the MUSIC method has the potential of localizing two closer incoherent dipole sources with a minimum lateral separation of 20 mm, versus 70 mm for the MVDR method, at a dipole-array distance of half the array length. Both localization methods have strong robustness to the vibrational state of the dipole source. Our work provides a promising and robust way to meet the high-resolution and multi-source sensing requirements of underwater vehicles.

Detection methods for milk pathogenic bacteria by loop-mediated isothermal amplification.

Milk is a common food, which is consumed all over the world. It is an important source of calcium. Meanwhile, it provides abundant protein, minerals and vitamins. However, pathogenic bacteria which exist in milk not only causes nutrition loss, but also produces toxins which may cause diarrhea, food poisoning, and even death. In order to control the microbial level of raw milk and eliminate the contamination of materials, this assay applied loop-mediated isothermal amplification to explore a new way to detect enterotoxigenic Escherichia coli (ETEC) in raw milk. The best reaction condition in detecting ETEC from raw milk was confirmed to be: 0.016 µM each of forward outer primer (primer F3) and backward outer primer (primer B3), 0.128 µM each of forward inner primer (primer FIP) and backward inner primer (primer BIP), 0.45 µM deoxy-ribonucleoside triphosphate (dNTPs), 2IU Bst DNA polymerase large fragment and template DNA were incubated at 63°C for 60 min. LAMP was proved to be specific, rapid and sensitive in detecting pathogenic bacteria which exist in milk.