AUV Obstacle Avoidance Planning Based on Deep Reinforcement Learning

In a complex underwater environment, finding a viable, collision-free path for an autonomous underwater vehicle (AUV) is a challenging task. The purpose of this paper is to establish a safe, real-time, and robust method of collision avoidance that improves the autonomy of AUVs. We propose a method based on active sonar, which utilizes a deep reinforcement learning algorithm to learn the processed sonar information to navigate the AUV in an uncertain environment. We compare the performance of double deep Q-network algorithms with that of a genetic algorithm and deep learning. We propose a line-of-sight guidance method to mitigate abrupt changes in the yaw direction and smooth the heading changes when the AUV switches trajectory. The different experimental results show that the double deep Q-network algorithms ensure excellent collision avoidance performance. The effectiveness of the algorithm proposed in this paper was verified in three environments: random static, mixed static, and complex dynamic. The results show that the proposed algorithm has significant advantages over other algorithms in terms of success rate, collision avoidance performance, and generalization ability. The double deep Q-network algorithm proposed in this paper is superior to the genetic algorithm and deep learning in terms of the running time, total path, performance in avoiding collisions with moving obstacles, and planning time for each step. After the algorithm is trained in a simulated environment, it can still perform online learning according to the information of the environment after deployment and adjust the weight of the network in real-time. These results demonstrate that the proposed approach has significant potential for practical applications.

Study on spacecraft formation capture control method based on disturbance observer

In the presence of compound disturbances, a multi-spacecraft cooperative collision avoidance capture control method based on disturbance observer was proposed, which can solve the problem of low speed rolling non-cooperative target close-range capture in space. Firstly, a relative motion model of attitude and orbit coupling is established. Secondly, the disturbance observer is used to estimate and cancel the compound disturbance in the capture process. At the same time, the hyperquadric surfaces are used to describe the shape of space non-cooperative targets and capture spacecraft to establish a composite artificial potential field, and a robust control law with collision avoidance function is also designed. Finally, the stability of the controlled system is proved by using Lyapunov function, and the collision avoidance performance of the system is analyzed. Numerical simulations are carried out to evaluate the effectiveness of the proposed control scheme.

Autonomous obstacle avoidance of UAV based on deep reinforcement learning1

In the intelligent unmanned systems, unmanned aerial vehicle (UAV) obstacle avoidance technology is the core and primary condition. Traditional algorithms are not suitable for obstacle avoidance in complex and changeable environments based on the limited sensors on UAVs. In this article, we use an end-to-end deep reinforcement learning (DRL) algorithm to achieve the UAV autonomously avoid obstacles. For the problem of slow convergence in DRL, a Multi-Branch (MB) network structure is proposed to ensure that the algorithm can get good performance in the early stage; for non-optimal decision-making problems caused by overestimation, the Revise Q-value (RQ) algorithm is proposed to ensure that the agent can choose the optimal strategy for obstacle avoidance. According to the flying characteristics of the rotor UAV, we build a V-Rep 3D physical simulation environment to test the obstacle avoidance performance. And experiments show that the improved algorithm can accelerate the convergence speed of agent and the average return of the round is increased by 25%.

Obstacle Detection System for Agricultural Mobile Robot Application Using RGB-D Cameras

Mobile robots designed for agricultural tasks need to deal with challenging outdoor unstructured environments that usually have dynamic and static obstacles. This assumption significantly limits the number of mapping, path planning, and navigation algorithms to be used in this application. As a representative case, the autonomous lawn mowing robot considered in this work is required to determine the working area and to detect obstacles simultaneously, which is a key feature for its working efficiency and safety. In this context, RGB-D cameras are the optimal solution, providing a scene image including depth data with a compromise between precision and sensor cost. For this reason, the obstacle detection effectiveness and precision depend significantly on the sensors used, and the information processing approach has an impact on the avoidance performance. The study presented in this work aims to determine the obstacle mapping accuracy considering both hardware- and information processing-related uncertainties. The proposed evaluation is based on artificial and real data to compute the accuracy-related performance metrics. The results show that the proposed image and depth data processing pipeline introduces an additional distortion of 38 cm.

Human Performance in Critical Scenarios as a Benchmark for Highly Automated Vehicles

Before highly automated vehicles (HAVs) become part of everyday traffic, their safety has to be proven. The use of human performance as a benchmark represents a promising approach, but appropriate methods to quantify and compare human and HAV performance are rare. By adapting the method of constant stimuli, a scenario-based approach to quantify the limit of (human) performance is developed. The method is applied to a driving simulator study, in which participants are repeatedly confronted with a cut-in manoeuvre on a highway. By systematically manipulating the criticality of the manoeuvre in terms of time to collision, humans’ collision avoidance performance is measured. The limit of human performance is then identified by means of logistic regression. The calculated regression curve and its inflection point can be used for direct comparison of human and HAV performance. Accordingly, the presented approach represents one means by which HAVs’ safety performance could be proven.

Establishing the Psychometric Properties of the Self-Report Liebowitz Social Anxiety Scale for Children and Adolescents in a General Population Adolescent Sample

The Liebowitz Social Anxiety Scale for Children and Adolescents (LSAS-CA) is a valid and reliable clinician-administered measure of social anxiety symptoms in young people. It has been adapted for self-report completion, and although the psychometric properties of this version of the scale have been examined in Spanish, Hebrew, and French language versions, this has not yet been done for the English language version. In the present study, we examined the factor structure and psychometric properties of the self-report version of the scale (LSAS-CA-SR) in a sample of UK adolescents recruited from schools. The factor structure of the scale was determined in our sample of N = 829; a four-factor structure, with interaction anxiety, interaction avoidance, performance anxiety, and performance-avoidance subscales, provided the best fit to the data. Measurement invariance of the scale was demonstrated across age and gender. Psychometric properties of the scale were sound, with good internal consistency (.88–.97), acceptable test-retest reliability (.45–.57), and evidence for convergent and divergent validity.

Scrophularia buergeriana Extract (Brainon) Improves Scopolamine-Induced Neuronal Impairment and Cholinergic Dysfunction in Mice through CREB-BDNF Signaling Pathway

We evaluated the effectiveness of Scrophularia buergeriana extract (Brainon) on cognitive dysfunction and determined its underlying mechanisms in a scopolamine (SCO)-treated mouse model of memory impairment. Brainon treatment for 28 days ameliorated the symptoms of memory impairment as indicated by the results of both passive avoidance performance and the Morris water mazes. Brainon lowered acetylcholinesterase activity and raised acetylcholine levels in the hippocampus. The treatment elevated the protein levels of brain-derived neurotrophic factor (BDNF) and phosphorylated cAMP response element-binding (CREB). Additionally, the excessive generation of SCO-induced reactive oxygen species (ROS) and subsequent oxidative stress were suppressed by the enhancement of superoxide dismutase (SOD)-1 and SOD-2 proteins. mRNA levels of upregulated interleukin (IL)-1β, IL-6, and tumor necrosis factor (TNF)-α, as well as the apoptotic protein Bcl-2-associated X protein (Bax), cleaved caspase-9, and cleaved poly adenosine diphosphate-ribose polymerase (PARP) expression after SCO injection were downregulated by Brainon treatment. Collectively, these findings suggested that Brainon possesses anti-amnesic effects through the CREB-BDNF pathway. Moreover, it exerted antioxidant, anti-inflammatory, and anti-apoptotic effects in SCO-induced mice exhibiting cognitive impairment and memory loss.

An obstacles avoidance method for serial manipulator based on reinforcement learning and Artificial Potential Field

The obstacles avoidance of manipulator is a hot issue in the field of robot control. Artificial Potential Field Method (APFM) is a widely used obstacles avoidance path planning method, which has prominent advantages. However, APFM also has some shortcomings, which include the inefficiency of avoiding obstacles close to target or dynamic obstacles. In view of the shortcomings of APFM, Reinforcement Learning (RL) only needs an automatic learning model to continuously improve itself in the specified environment, which makes it capable of optimizing APFM theoretically. In this paper, we introduce an approach hybridizing RL and APFM to solve those problems. We define the concepts of Distance reinforcement factors (DRF) and Force reinforcement factors (FRF) to make RL and APFM integrated more effectively. We disassemble the reward function of RL into two parts through DRF and FRF, and make them activate in different situations to optimize APFM. Our method can obtain better obstacles avoidance performance through finding the optimal strategy by RL, and the effectiveness of the proposed algorithm is verified by multiple sets of simulation experiments, comparative experiments and physical experiments in different types of obstacles. Our approach is superior to traditional APFM and the other improved APFM method in avoiding collisions and approaching obstacles avoidance. At the same time, physical experiments verify the practicality of the proposed algorithm.

How Proponents and Opponents Influence Achievement Motivation: The Role of the Anticipated Emotions of Other People

There are countless studies about the influence of other people’s emotions on individuals' behavior. However, the influence of proponents' and opponents' future emotions on achievement motivation remains unclear. This study aims to fill this gap. Therefore, departing from the emotional intelligence theory, the author materializes the anticipated emotions of other people concept and tests it using a static group experimental design with success and failure scenarios, involving 203 participants chosen judgmentally. When reminded of the proponents' joyfulness caused by their success, the Mann-Whitney U test with normal approximation, supported by the Monte Carlo estimation, shows that the mastery-avoidance, performance-approach, and performance-avoidance goals of the experimental group are enhanced. Whereas, when reminded that they would be envied and make the opponents feel distressed, the performance-approach goals are improved. In the failure scenario, when the participants were directed to the proponents' distress, as a response to their failure, the four components of the achievement goals are increased: mastery-approach, mastery-avoidance, performance-approach, and performance-avoidance. However, the opponents' joyfulness, anticipated as a malicious schadenfreude to the participants' failure, is only successful in stimulating the performance-avoidance goals. A Bayesian estimate with 5,000 times bootstrapping reveals that self-efficacy mediates the influence of the proponents' anticipated joyfulness on the mastery-approach fully, and on the performance-approach goals in a complementary way. Complementary mediation is also apparent in the impact of the proponents' distress on the mastery-approach and mastery-avoidance goals. Above all, love for the proponents is more potent than hatred from social environments for increasing the achievement motivation. Further research is encouraged to replicate this study with different social behavior.

Sliding control method of marine ecological protection robot

In order to solve the problem of low control accuracy of the marine ecological protection robot in the route planning process during positioning, a new sliding control method is proposed. First, obtain the position information of the marine ecological protection robot, use the dynamic information measurement method to process the dynamic information, and extract the position tracking information. According to the needs of dynamic positioning and target path tracking, combined with the robot sliding control method, the global positioning of the marine ecological protection robot is designed. Experiments show that this method has high positioning accuracy for marine ecological protection robots, small positioning errors, good obstacle avoidance performance and strong dynamic positioning control capabilities.