Collision-free parking recommendation based on multi-agent reinforcement learning in vehicular crowdsensing

The recent proliferation of Fifth-Generation(5G)networks and Sixth-Generation(6G)networks has given rise to Vehicular Crowd Sensing(VCS)systems which solve parking collisions by effectively incentivizing vehicle participation.However,instead of being an isolated module,the incentive mechanism usually interacts with other modules.Based on this,we capture this synergy and propose a Collision-free Parking Recommendation(CPR),a novel VCS system framework that integrates an incentive mechanism,a non-cooperative VCS game,and a multi-agent reinforcement learning algorithm,to derive an optimal parking strategy in real time.Specifically,we utilize an LSTM method to predict parking areas roughly for recommendations accurately.Its incentive mechanism is designed to motivate vehicle participation by considering dynamically priced parking tasks and social network effects.In order to cope with stochastic parking collisions,its non-cooperative VCS game further analyzes the uncertain interactions between vehicles in parking decision-making.Then its multi-agent reinforcement learning algorithm models the VCS campaign as a multi-agent Markov decision process that not only derives the optimal collision-free parking strategy for each vehicle independently,but also proves that the optimal parking strategy for each vehicle is Pareto-optimal.Finally,numerical results demonstrate that CPR can accomplish parking tasks at a 99.7%accuracy compared with other baselines,efficiently recommending parking spaces.

Research on the Collision-Free Path Planning of Multi-AGVs System Based on Improved A* Algorithm

Path planning problem is the core and hot research topic of multiple Automatic Guided Vehicles (multi-AGVs) system. Although there are many research results, they do not solve the path planning problem from the perspective of reducing traffic congestion. A collision-free path planning method based on improved A* Algorithm for multi-AGVs logistics sorting system is proposed in this paper. In the method, the environment of warehouse operation for AGVs is described by using grid method. The estimated cost of A* algorithm is improved by adding the penalty value of the paths that AGVs share with each other to alleviate traffic congestion and collision resolution rules are made according to different types of collisions. Then the collision-free path planning is done by combing the improved A* algorithm and collision resolution rules. The sorting efficiency of the method is compared with that of original A* algorithm. Simulation results show that the new collision-free path planning method can improve the sorting efficiency of multi-AGVs system and relieve traffic congestion.

Tool selection and collision-free in 5-axis numerical control machining of free-form surfaces

The methodology of 5-axis cutter selection to avert collision for free-form surface machining by flat-end cutters is presented. The combination of different cutters is adopt aiming at short machining time and high precision. The optimal small cutter is determined based on the geometric information of the points where a cutter most probably collide with the machined surface. Several larger cutters are selected to machine the surface in order to find the interference-free area. The difference of machining time for this area between the optimal small cutter and the large cutters is calculated. The functional relationship between the machining time and the radius of a cutter is established, by which the optimal number of cutters is obtained. The combination of cutters, which possesses the minimum overall machining time, is selected as the optimal cutter sizes. A case study has demonstrated the validity of the proposed methodology and algorithms.

The collision-free trajectory planning for the space robot to capture a target based on the wavelet interpolation algorithm

In the research of path planning for manipulators with many DOF, generally there is a problem in most traditional methods, which is that their computational cost (time and memory space) increases exponentially as DOF or resolution of the discrete configuration space increases. So this paper presents the collision-free trajectory planning for the space robot to capture a target based on the wavelet interpolation algorithm. We made wavelet sample on the desired trajectory of the manipulator’s end-effector to do trajectory planning by use of the proposed wavelet interpolation formula, and then derived joint vectors from the trajectory information of the end-effector based on the fixed-attitude-restrained generalized Jacobian matrix of multi-arm coordinated motion, so as to control the manipulator to capture a static body along the desired collision-free trajectory. The method overcomes the shortcomings of the typical methods, and the desired trajectory of the end-effector can be any kind of complex nonlinear curve. The algorithm is simple and highly effective and the real trajectory is close to the desired trajectory. In simulation, the planar dual-arm three DOF space robot is used to demonstrate the proposed method, and it shows that the algorithm is feasible.

Efficiently constructing collision-free regions of tool orientations for holder in five-axis machining of blisk

Blisks with the integral structure are key parts used in new jet engines to promote the performance of aircrafts,which also increases the complexity of tool orientation planning in the five-axis machining.It is an essential task to find the collision-free tool orientation when the tool holder is pushed deep into the channel of blisk to increase rigidity and reduce vibration.Since the radius of the holder varies with the height,the line-visibility is no longer applicable when constructing collision-free regions of tool orientation.In this paper,a method of constructing collisionfree regions without interference checking is proposed.The work of finding collision-free regions resorts to solving the local contact curves on the checking surfaces of blisk.And it further transforms into searching the locally tangent points(named critical points)between the holder and surface.Then a tracking-based algorithm is proposed to search the sample critical points on these local contact curves.And the corresponding critical vectors are also calculated synchronously.Besides,the safety allowance,discrete precision and acceptable deviation are introduced in the algorithm to ensure accuracy by controlling the angle between two adjacent critical vectors properly.After that,the searched critical vectors are mapped orderly to two-dimensional space and the collisionfree regions are constructed.This method is finally verified and compared with a referenced method.The results show that the proposed method can efficiently construct collision-free regions for holder under the given accuracy.

Motion Planning Algorithm and Simulation for Space Manipulators

The specificities of collision-free path planning of space manipulators are analyzed. Path planning strategies are presented in consideration of these specificities, and an implementation procedure is also described in detail according to these strategies.