Novel learning framework for optimal multi-object video trajectory tracking

Background With the rapid development of Web3D, virtual reality, and digital twins, virtual trajectories and decision data considerably rely on the analysis and understanding of real video data, particularly in emergency evacuation scenarios. Correctly and effectively evacuating crowds in virtual emergency scenarios are becoming increasingly urgent. One good solution is to extract pedestrian trajectories from videos of emergency situations using a multi-target tracking algorithm and use them to define evacuation procedures. Methods To implement this solution, a trajectory extraction and optimization framework based on multi-target tracking is developed in this study. First, a multi-target tracking algorithm is used to extract and preprocess the trajectory data of the crowd in a video. Then, the trajectory is optimized by combining the trajectory point extraction algorithm and Savitzky-Golay smoothing filtering method. Finally, related experiments are conducted, and the results show that the proposed approach can effectively and accurately extract the trajectories of multiple target objects in real time. Results In addition, the proposed approach retains the real characteristics of the trajectories as much as possible while improving the trajectory smoothing index, which can provide data support for the analysis of pedestrian trajectory data and formulation of personnel evacuation schemes in emergency scenarios. Conclusions Further comparisons with methods used in related studies confirm the feasibility and superiority of the proposed framework.

Regularizing fuel-optimal multi-impulse trajectories

The regularization theory has successfully enabled the removal of gravitational singularities associated with celestial bodies.In this study,regularizing techniques are merged into a multi-impulse trajectory design framework that requires delicate computations,particularly for a fuel minimization problem.Regularized variables based on the Levi–Civita or Kustaanheimo–Stiefel transformations express instantaneous velocity changes in a gradient-based direct optimization method.The formulation removes the adverse singularities associated with the null thrust impulses from the derivatives of an objective function in the fuel minimization problem.The favorite singularity-free property enables the accurate reduction of unnecessary impulses and the generation of necessary impulses for local optimal solutions in an automatic manner.Examples of fuel-optimal multi-impulse trajectories are presented,including novel transfer solutions between a near-rectilinear halo orbit and a distant retrograde orbit.

Smart Gait:A Gait Optimization Framework for Hexapod Robots

The current gait planning for legged robots is mostly based on human presets,which cannot match the flexible characteristics of natural mammals.This paper proposes a gait optimization framework for hexapod robots called Smart Gait.Smart Gait contains three modules:swing leg trajectory optimization,gait period&duty optimization,and gait sequence optimization.The full dynamics of a single leg,and the centroid dynamics of the overall robot are considered in the respective modules.The Smart Gait not only helps the robot to decrease the energy consumption when in locomotion,mostly,it enables the hexapod robot to determine its gait pattern transitions based on its current state,instead of repeating the formalistic clock-set step cycles.Our Smart Gait framework allows the hexapod robot to behave nimbly as a living animal when in 3D movements for the first time.The Smart Gait framework combines offline and online optimizations without any fussy data-driven training procedures,and it can run efficiently on board in real-time after deployment.Various experiments are carried out on the hexapod robot LittleStrong.The results show that the energy consumption is reduced by 15.9%when in locomotion.Adaptive gait patterns can be generated spontaneously both in regular and challenge environments,and when facing external interferences.

Increasing realism in modelling energy losses in railway vehicles and their impact to energy-efficient train control

The reduction of energy consumption is an increasingly important topic of the railway system.Energy-efficient train control(EETC)is one solution,which refers to mathematically computing when to accelerate,which cruising speed to hold,how long one should coast over a suitable space,and when to brake.Most approaches in literature and industry greatly simplify a lot of nonlinear effects,such that they ignore mostly the losses due to energy conversion in traction components and auxiliaries.To fill this research gap,a series of increasingly detailed nonlinear losses is described and modelled.We categorize an increasing detail in this representation as four levels.We study the impact of those levels of detail on the energy optimal speed trajectory.To do this,a standard approach based on dynamic programming is used,given constraints on total travel time.This evaluation of multiple test cases highlights the influence of the dynamic losses and the power consumption of auxiliary components on railway trajectories,also compared to multiple benchmarks.The results show how the losses can make up 50%of the total energy consumption for an exemplary trip.Ignoring them would though result in consistent but limited errors in the optimal trajectory.Overall,more complex trajectories can result in less energy consumption when including the complexity of nonlinear losses than when a simpler model is considered.Those effects are stronger when the trajectory includes many acceleration and braking phases.

Optimal midcourse trajectory cluster generation and trajectory modification for hypersonic interceptions

The hypersonic interception in near space is a great challenge because of the target’s unpredictable trajectory, which demands the interceptors of trajectory cluster coverage of the predicted area and optimal trajectory modification capability aiming at the consistently updating predicted impact point(PIP) in the midcourse phase. A novel midcourse optimal trajectory cluster generation and trajectory modification algorithm is proposed based on the neighboring optimal control theory. Firstly, the midcourse trajectory optimization problem is introduced; the necessary conditions for the optimal control and the transversality constraints are given.Secondly, with the description of the neighboring optimal trajectory existence theory(NOTET), the neighboring optimal control(NOC)algorithm is derived by taking the second order partial derivations with the necessary conditions and transversality conditions. The revised terminal constraints are reversely integrated to the initial time and the perturbations of the co-states are further expressed with the states deviations and terminal constraints modifications.Thirdly, the simulations of two different scenarios are carried out and the results prove the effectiveness and optimality of the proposed method.

Application of Optimal-Jerk Trajectory Planning in Gait-balance Training Robot

To accommodate the gait and balance disorder of the elderly with age progression and the occurrence of various senile diseases,this paper proposes a novel gait balance training robot(G-Balance)based on a six degree-of-freedom parallel platform.Using the platform movement and IMU wearable sensors,two training modes,i.e.,active and passive,are developed to achieve vestibular stimulation.Virtual reality technology is applied to achieve visual stimulation.In the active training mode,the elderly actively exercises to control the posture change of the platform and the switching of the virtual scene.In the passive training mode,the platform movement is combined with the virtual scene to simulate bumpy environments,such as earthquakes,to enhance the human anti-interference ability.To achieve a smooth switching of the scene,continuous speed and acceleration of the platform motion are required in some scenarios,in which a trajectory planning algorithm is applied.This paper describes the application of the trajectory planning algorithm in the balance training mode and the optimization of jerk(differential of acceleration)based on cubic spline planning,which can reduce impact on the joint and enhance stability.

Multi-objective Optimal Trajectory and Placement of a Robot for Cotton Yarns Handling

This study deals with a robot manipulator for yarn bobbin handling in the cotton yarns lattice distortion modification system.The aim is to achieve an operation of yarn bobbin handling with minimal execution time,energy consumption and jerk in motion together.The placement of the robot,in relation to the yarn bobbin stations,is also optimized in conjunction of trajectory optimization.Three possible techniques for building the handling traj'ectory were considered:the quaternion spherical linear interpolation in Cartesian space,the quintic polynomial spline and quintic B-spline in joint space.The genetic algorithm(GA) was used to optimize the trajectories of the robot,with a penalty function to handle nonlinear constraints associated in the robot motion.Two simulations of the optimal trajectory in joint space and the placement of robot were carried out and the results obtained were presented and discussed.It is concluded that the quintic polynomial spline constructs a better trajectory in joint space and the proper placement of robot makes better performance.

A CALCULATION OF OPTIMAL FLIGHT TRAJECTORY USING THE PARAMETERIZED OPTIMIZATION METHOD

ＡＣＡＬＣＵＬＡＴＩＯＮＯＦＯＰＴＩＭＡＬＦＬＩＧＨＴＴＲＡＪＥＣＴＯＲＹＵＳＩＮＧＴＨＥＰＡＲＡＭＥＴＥＲＩＺＥＤＯＰＴＩＭＩＺＡＴＩＯＮＭＥＴＨＯＤＡＣＡＬＣＵＬＡＴＩＯＮＯＦＯＰＴＩＭＡＬＦＬＩＧＨＴＴＲＡＪＥＣＴＯＲＹＵＳＩＮＧＴＨＥＰＡＲＡ...

Optimal Trajectory Planning of the Dual Arm Manipulator Using DAMM

This paper presents an optimal trajectory planning method of the dual arm manipulator using Dual Arm Manipulability Measure （DAMM）. When the manipulator carries an object from a certain position to the destination, various trajectory candidates could be conskied. TO select the optimal trajectacy from the several candidates, energy, time, and the length of the tmjecttay could be utilized. In order to quantify the carrying effidency of dual-arms, DAMM has been defined and applied for the decision of the optimal path. DAMM is defined as the interaction of the manipulability ellipsoids of the dualarras, while the manipulability measure irdicates the relationship between the joint velocity and the Cartesian velocity for each ann. The cast function for achieving the optimal path is defined as the Summation of the distance to the goal and inverse of this DAMM, which aims to generate the efficient motion to the goal. It is confirmed that the optimal path planning keeps higher manipulability through the short distance path by using computer simulation. To show the effectiveness of this cooperative control algorithm experimentally, a 5-DOF dual-ann robot with distributed controllers for synchronization control has been developed and used for the experiments.

Optimal Rendezvous Sequence for LEO Debris Capture

The primary purpose of this study is to exploit the effect of Earth＇s non-sphericity perturbation, particularly due to the J2 term, in order to optimize the capture sequence of potential orbital debris, that is the cumulative AV associated to the transfers between one object and the others. As results of several researches and model predictions, many international agencies agree that the growing population of objects and debris in LEO （low earth orbits）, will follow a diverging trend in the future. This, in turn, would constitute a serious threat to circum-terrestrial space safety and sustainability. In LEO, the ,J disturbance is prevailing over the others, and it acts by affecting the longitude of the ascending node （Ω）, the argument of perigee （ω） and, accordingly, the true anomaly （v）. Therefore, the goal of optimizing the AV is achieved by taking advantage of the rate of variation of Ω and ω, thereby compensating for the △Ω and △ω, present between the orbital transfer vehicle （chaser） and the debris to be captured （target）. Obviously, the perturbation will lead to favourable variations of the orbital parameters only for some combinations of Ω and ω. Yet the presence of a debris population with random distribution of Ω and ω, makes this application particularly suited to the problem. The single maneuver has been modelled with a 4-impulse time fixed rendezvous and the optimization problem has been addressed by implementing a hybrid evolutionary algorithm, which adopts, in parallel, three different strategies, namely, genetic algorithm, differential evolution and particle swarm optimization.

Optimal trajectory planning for natural biped walking locomotion

An optimal trajectory planning method has been proposed for the walking locomotion of a biped mechanical system with thighs, shanks and small feet, which is modelled as a 3 DOF link system consisting of an inverted pendulum and a 2 DOF swing leg. The locomotion of swing and supporting legs is solved by the optimal trajectory planning based on function approximation. The optimal trajectory planning based on function approximation. The optimal walking locomotion solution with minimum square of input torque exhibits a natural walking gait with one step period of 0.64 s similar to the human walking gait by using the link parameters of an adult’s leg. It is concluded from the computation results that the method proposed in this paper has been proved to be an effective tool for solving the optimal walking locomotion and joint control torque problems for a 3 DOF biped mechanism; when the ankle joint of the supporting leg is a passive joint, a nearly, optimal walking solution can be obtained at t 1=0.49 s and t 2=10 s, and however, when the knee is a passive joint, it is impossible to obtain a solution which satisfies the constraint condition; for the link parameters used in this paper, the length of an optimal stride is 0.3 m.

Optimal Release Control of Companion Satellite System Using Electromagnetic Forces

Electromagnetic forces generated by the inter-action of component satellites can be used to release companion satellites. Optimal release trajectories for companion satellite system using inter-electromagnetic forces were investigated. Firstly,nonlinear relative motion dynamic equations of a two-craft electromagnetic companion satellite system were derived in spatial polar coordinates. Then principles of electromagnetic satellite formation flying were introduced. Secondly,the characteristics of the electromagnetic companion satellites release were analyzed and optimal release trajectories of companion satellites using electromagnetic forces were obtained using Gauss pseudospectral method. Three performance criteria were chosen as minimum time,minimum acceleration of the separation distance and minimum control acceleration. Finally,three release examples including expansion along separation distance, rotation in orbital plane and stable formation reconfiguration were given to demonstrate the feasibility of this method. Results indicated that the release trajectories can converge to optimal solutions effectively and the concept of release companion satellites using electromagnetic forces is practicable.

UAVs cooperative task assignment and trajectory optimization with safety and time constraints

This paper proposes new methods and strategies for Multi-UAVs cooperative attacks with safety and time constraints in a complex environment.Delaunay triangle is designed to construct a map of the complex flight environment for aerial vehicles.Delaunay-Map,Safe Flight Corridor(SFC),and Relative Safe Flight Corridor(RSFC)are applied to ensure each UAV flight trajectory's safety.By using such techniques,it is possible to avoid the collision with obstacles and collision between UAVs.Bezier-curve is further developed to ensure that multi-UAVs can simultaneously reach the target at the specified time,and the trajectory is within the flight corridor.The trajectory tracking controller is also designed based on model predictive control to track the planned trajectory accurately.The simulation and experiment results are presented to verifying developed strategies of Multi-UAV cooperative attacks.

Optimal impulsive rendezvous for highly elliptical orbits using linear primer vector theory

In this paper,minimum-fuel rendezvous is investigated for the case in which the reference orbit is highly elliptic.To this end,the well-known Tschauner-Hempel equations are used to describe the relative motions between rendezvous spacecraft and the target.Lawden’s primer vector theory is then applied on this linear but time-varying system.The analytical solution of the required primer vector for this problem is then derived by using a recently developed method.For the existing non-optimal solutions which don’t satisfy the conditions,the methods are further designed to improve the performance by shifting impulses or adding a new one.Finally,two algorithms are developed for free-impulse time-fixed rendezvous problems.The first algorithm can determine the globally optimal trajectory with the optimal number of impulses.The second one enables for fast trajectory planning.The proposed algorithms have been successfully applied to coplanar and three-dimensional rendezvous problems in which the target is flying on highly elliptical orbits.

NOMA Empowered Energy Efficient Data Collection and Wireless Power Transfer in Space-Air-Ground Integrated Networks

As the sixth generation network(6G)emerges,the Internet of remote things(IoRT)has become a critical issue.However,conventional terrestrial networks cannot meet the delay-sensitive data collection needs of IoRT networks,and the Space-Air-Ground integrated network(SAGIN)holds promise.We propose a novel setup that integrates non-orthogonal multiple access(NOMA)and wireless power transfer(WPT)to collect latency-sensitive data from IoRT networks.To extend the lifetime of devices,we aim to minimize the maximum energy consumption among all IoRT devices.Due to the coupling between variables,the resulting problem is non-convex.We first decouple the variables and split the original problem into four subproblems.Then,we propose an iterative algorithm to solve the corresponding subproblems based on successive convex approximation(SCA)techniques and slack variables.Finally,simulation results show that the NOMA strategy has a tremendous advantage over the OMA scheme in terms of network lifetime and energy efficiency,providing valuable insights.

An AutoML based trajectory optimization method for long-distance spacecraft pursuit-evasion game

Current successes in artificial intelligence domain have revitalized interest in spacecraft pursuit-evasion game,which is an interception problem with a non-cooperative maneuvering target.The paper presents an automated machine learning(AutoML)based method to generate optimal trajectories in long-distance scenarios.Compared with conventional deep neural network(DNN)methods,the proposed method dramatically reduces the reliance on manual intervention and machine learning expertise.Firstly,based on differential game theory and costate normalization technique,the trajectory optimization problem is formulated under the assumption of continuous thrust.Secondly,the AutoML technique based on sequential model-based optimization(SMBO)framework is introduced to automate DNN design in deep learning process.If recommended DNN architecture exists,the tree-structured Parzen estimator(TPE)is used,otherwise the efficient neural architecture search(NAS)with network morphism is used.Thus,a novel trajectory optimization method with high computational efficiency is achieved.Finally,numerical results demonstrate the feasibility and efficiency of the proposed method.

Autonomous UAV 3D trajectory optimization and transmission scheduling for sensor data collection on uneven terrains

This paper considers a time-constrained data collection problem from a network of ground sensors located on uneven terrain by an Unmanned Aerial Vehicle(UAV),a typical Unmanned Aerial System(UAS).The ground sensors harvest renewable energy and are equipped with batteries and data buffers.The ground sensor model takes into account sensor data buffer and battery limitations.An asymptotically globally optimal method of joint UAV 3D trajectory optimization and data transmission schedule is developed.The developed method maximizes the amount of data transmitted to the UAV without losses and too long delays and minimizes the propulsion energy of the UAV.The developed algorithm of optimal trajectory optimization and transmission scheduling is based on dynamic programming.Computer simulations demonstrate the effectiveness of the proposed algorithm.

Cooperative trajectory optimization of UAVs in approaching stage using feedback guidance methods

This paper mainly studies the problem of using UAVs to provide accurate remote target indication for hypersonic projectiles.Based on the optimal trajectory trends and feedback guidance methods,a new cooperative control algorithm is proposed to optimize trajectories of multi-UAVs for target tracking in approaching stage.Based on UAV kinematics and sensor performance models,optimal trajectory trends of UAVs are analyzed theoretically.Then,feedback guidance methods are proposed under the optimal observation trends of UAVs in the approaching target stage,producing trajectories with far less computational complexity and performance very close to the best-known trajectories.Next,the sufficient condition for the UAV to form the optimal observation configuration by the feedback guidance method is presented,which guarantees that the proposed method can optimize the observation trajectory of the UAV in approaching stage.Finally,the feedback guidance method is numerically simulated.Simulation results demonstrate that the estimation performance of the feedback guidance method is superior to the Lyapunov guidance vector field(LGVF)method and verify the effectiveness of the proposed method.Additionally,compared with the receding horizon optimization(RHO)method,the proposed method has the same optimization ability as the RHO method and better real-time performance.

Optimal interplanetary trajectories for Sun-facing ideal diffractive sails

A diffractive sail is a solar sail whose exposed surface is covered by an advanced diffractive metamaterial film with engineered optical properties. This study examines the optimal performance of a diffractive solar sail with a Sun-facing attitude in a typical orbit-to-orbit heliocentric transfer. A Sun-facing attitude, which can be passively maintained through the suitable design of the sail shape, is obtained when the sail nominal plane is perpendicular to the Sun–spacecraft line. Unlike an ideal reflective sail, a Sun-facing diffractive sail generates a large transverse thrust component that can be effectively exploited to change the orbital angular momentum. Using a recent thrust model, this study determines the optimal control law of a Sun-facing ideal diffractive sail and simulates the minimum transfer times for a set of interplanetary mission scenarios. It also quantifies the performance difference between Sun-facing diffractive sail and reflective sail. A case study presents the results of a potential mission to the asteroid 16 Psyche.

A train timetable rescheduling approach based on multi-train tracking optimization of high-speed railways

Purpose–This paper aims to propose a train timetable rescheduling(TTR)approach from the perspective of multi-train tracking optimization based on the mutual spatiotemporal information in the high-speed railway signaling system.Design/methodology/approach–Firstly,a single-train trajectory optimization(STTO)model is constructed based on train dynamics and operating conditions.The train kinematics parameters,including acceleration,speed and time at each position,are calculated to predict the arrival times in the train timetable.A STTO algorithm is developed to optimize a single-train time-efficient driving strategy.Then,a TTR approach based on multi-train tracking optimization(TTR-MTTO)is proposed with mutual information.The constraints of temporary speed restriction(TSR)and end of authority are decoupled to calculate the tracking trajectory of the backward tracking train.The multi-train trajectories at each position are optimized to generate a timeefficient train timetable.Findings–The numerical experiment is performed on the Beijing-Tianjin high-speed railway line and CR400AF.The STTO algorithm predicts the train’s planned arrival time to calculate the total train delay(TTD).As for the TSR scenario,the proposed TTR-MTTO can reduce TTD by 60.60%compared with the traditional TTR approach with dispatchers’experience.Moreover,TTR-MTTO can optimize a time-efficient train timetable to help dispatchers reschedule trains more reasonably.Originality/value–With the cooperative relationship and mutual information between train rescheduling and control,the proposed TTR-MTTO approach can automatically generate a time-efficient train timetable to reduce the total train delay and the work intensity of dispatchers.