Cooperative Trajectory Planning for Automated Farming

2013 ◽  
Author(s):  
Charles Remeikas ◽  
Yunjun Xu ◽  
Suhada Jayasuriya
Keyword(s):  
Trajectory Planning ◽  
Computational Cost ◽  
Computation Cost ◽  
Agricultural Robots ◽  
Planning Algorithm ◽  
And Performance ◽  
Citrus Harvesting ◽  
Low Computational Cost ◽  
Pursuit Strategy ◽  
Cooperative Planning

Many agricultural tasks, such as harvesting, are labor intensive. With the interests in autonomous farming, a method to rapidly generate trajectories for agricultural robots satisfying different realistic constraints becomes necessary. A hierarchical cooperative planning method is studied in this paper for a group of agricultural robots with a low computational cost. Two parts are involved in the method: once a reconfiguration event is confirmed, all the possible formation configurations will be evaluated and ranked according to their feasibility and performance index; a local pursuit strategy based cooperative trajectory planning algorithm is designed to generate optimal cooperative trajectories for robots to achieve and maintain their desired formation. To help reduce the computation cost associated with the cooperative planning algorithm, early termination conditions are proposed. The capabilities of the proposed cooperative planning algorithm are demonstrated in a simple citrus harvesting problem.

Task Assignment and Trajectory Planning Algorithm for a Class of Cooperative Agricultural Robots

2015 ◽  
Vol 137 (5) ◽  
Author(s):  
Ni Li ◽  
Charles Remeikas ◽  
Yunjun Xu ◽  
Suhada Jayasuriya ◽  
Reza Ehsani
Keyword(s):  
Trajectory Planning ◽  
Task Assignment ◽  
Agricultural Field ◽  
Individual Level ◽  
Agricultural Robots ◽  
Hierarchical Decision ◽  
Planning Algorithm ◽  
The Individual ◽  
Citrus Harvesting ◽  
Level Performance

Agricultural field operations, such as harvesting for fruits and scouting for disease, are labor intensive and time consuming. With the recent push toward autonomous farming, a method to rapidly generate trajectories for a group of cooperative agricultural robots becomes necessary. The challenging aspect of solving this problem is to satisfy realistic constraints such as changing environments, actuation limitations, nonlinear heterogeneous dynamics, conflict resolution, and formation reconfigurations. In this paper, a hierarchical decision making and trajectory planning method is studied for a group of agricultural robots cooperatively conducting certain farming task such as citrus harvesting. Within the algorithm framework, there are two main parts (cooperative level and individual level): (1) in the cooperative level, once a discrete reconfiguration event is confirmed and replanning is triggered, all the possible formation configurations and associated robot locations for specific farming tasks will be evaluated and ranked according to the feasibility condition and the cooperative level performance index; and (2) in the individual level, a local pursuit (LP) strategy based cooperative trajectory planning algorithm is designed to generate local optimal cooperative trajectories for agricultural robots to achieve and maintain their desired operation formation in a decentralized manner. The capabilities of the proposed method are demonstrated in a citrus harvesting problem.

Optimal Trajectory Generation for Robotic Manipulators Using Dynamic Programming

1987 ◽  
Vol 109 (2) ◽  
pp. 88-96 ◽  
Author(s):  
S. Singh ◽  
M. C. Leu
Keyword(s):  
Dynamic Programming ◽  
Trajectory Planning ◽  
Optimal Trajectory ◽  
Robotic Manipulators ◽  
Planning Algorithm ◽  
Manipulator Link ◽  
On Line ◽  
And Performance ◽  
Two Stages ◽  
Optimal Trajectory Planning

The problem of optimal control of robotic manipulators is dealt with in two stages: (1) optimal trajectory planning, which is performed off-line and results in the prescription of the position and velocity of each link as a function of time along a “given” path and (2) on-line trajectory tracking, during which the manipulator is guided along the planned trajectory using a feedback control algorithm. In order to obtain a general trajectory planning algorithm which could account for various constraints and performance indices, the technique of dynamic programming is adopted. It is shown that for a given path, this problem is reduced to a search over the velocity of one moving manipulator link. The design of the algorithm for optimal trajectory planning and the relevant computational issues are discussed. Simulations are performed to test the effectiveness of this method. The use of this algorithm in conjunction with an on-line controller is also presented.

Trajectory planning and combined control design for critical high-speed lane change manoeuvres

2019 ◽  
Vol 234 (2-3) ◽  
pp. 823-839
Author(s):  
Hadi Sazgar ◽  
Shahram Azadi ◽  
Reza Kazemi
Keyword(s):  
Trajectory Planning ◽  
High Speed ◽  
Tracking Error ◽  
Computational Cost ◽  
Control Design ◽  
Lane Change ◽  
Driver Assistance ◽  
Yaw Stability ◽  
Combined Control ◽  
Low Computational Cost

The purpose of this research is to develop an advanced driver assistance system for the integrated longitudinal and lateral guidance of vehicles in critical high-speed lane change manoeuvres. The system consists of two parts: trajectory planning and combined control. At the first, by considering the TV position and the available range of longitudinal acceleration, several trajectories with different accelerations are generated. Then, by taking into account the vehicle and tyre dynamics, the most appropriate trajectory is selected. Therefore, the chosen trajectory is collision free and dynamically feasible. Because the trajectory planning is carried out algebraically, it has low computational cost. This is especially valuable in the experimental implementations. At the second part of the study, using a robust combined longitudinal-lateral controller, the control inputs are determined and transmitted to the brake/throttle and steering actuators. Both in the trajectory planning and combined control design, the nonlinear tyre dynamics and the dynamics of throttle and brake actuators are considered. To evaluate the performance of the proposed guidance algorithm, a full CarSim dynamic model is utilized. The simulation results for critical high-speed lane change manoeuvres confirm that the proposed trajectory planning method works effectively. The tracking error is also very small and the yaw stability is guaranteed.

scholarly journals Navigation of Autonomous Light Vehicles Using an Optimal Trajectory Planning Algorithm

2021 ◽  
Vol 13 (3) ◽  
pp. 1233
Author(s):  
Ángel Valera ◽  
Francisco Valero ◽  
Marina Vallés ◽  
Antonio Besa ◽  
Vicente Mata ◽  
...  
Keyword(s):  
Energy Consumption ◽  
Trajectory Planning ◽  
Autonomous Navigation ◽  
Optimal Trajectory ◽  
Computational Cost ◽  
Initial Point ◽  
Target Point ◽  
Software Components ◽  
Planning Algorithm ◽  
Optimal Trajectory Planning

Autonomous navigation is a complex problem that involves different tasks, such as location of the mobile robot in the scenario, robotic mapping, generating the trajectory, navigating from the initial point to the target point, detecting objects it may encounter in its path, etc. This paper presents a new optimal trajectory planning algorithm that allows the assessment of the energy efficiency of autonomous light vehicles. To the best of our knowledge, this is the first time in the literature that this is carried out by minimizing the travel time while considering the vehicle’s dynamic behavior, its limitations, and with the capability of avoiding obstacles and constraining energy consumption. This enables the automotive industry to design environmentally sustainable strategies towards compliance with governmental greenhouse gas (GHG) emission regulations and for climate change mitigation and adaptation policies. The reduction in energy consumption also allows companies to stay competitive in the marketplace. The vehicle navigation control is efficiently implemented through a middleware of component-based software development (CBSD) based on a Robot Operating System (ROS) package. It boosts the reuse of software components and the development of systems from other existing systems. Therefore, it allows the avoidance of complex control software architectures to integrate the different hardware and software components. The global maps are created by scanning the environment with FARO 3D and 2D SICK laser sensors. The proposed algorithm presents a low computational cost and has been implemented as a new module of distributed architecture. It has been integrated into the ROS package to achieve real time autonomous navigation of the vehicle. The methodology has been successfully validated in real indoor experiments using a light vehicle under different scenarios entailing several obstacle locations and dynamic parameters.

Method for Lumped Parameter Simulation of Digital Displacement Pumps/Motors Based on CFD

2013 ◽  
Vol 397-400 ◽  
pp. 615-620 ◽  
Author(s):  
Daniel Beck Roemer ◽  
Per Johansen ◽  
Henrik C. Pedersen ◽  
Torben O. Andersen
Keyword(s):  
Computational Cost ◽  
Simulation Models ◽  
Lumped Parameter Model ◽  
Model Parameters ◽  
Lumped Parameter ◽  
Displacement Pump ◽  
Variable Displacement ◽  
And Performance ◽  
And Control ◽  
Low Computational Cost

Digital displacement fluid power pumps/motors offers improved efficiency and performance compared to traditional variable displacement pump/motors. These improvements are made possible by using efficient electronically controlled seat valves and careful design of the flow geometry. To optimize the design and control of digital displacement machines, there is a need for simulation models, preferably models with low computational cost. Therefore, a low computational cost generic lumped parameter model of digital displacement machine is presented, including a method for determining the needed model parameters based on steady CFD results, in order to take detailed geometry information into account. The response of the lumped parameter model is compared to a computational expensive transient CFD model for an example geometry.

scholarly journals Emotion Recognition on Edge Devices: Training and Deployment

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4496
Author(s):  
Vlad Pandelea ◽  
Edoardo Ragusa ◽  
Tommaso Apicella ◽  
Paolo Gastaldo ◽  
Erik Cambria
Keyword(s):  
Emotion Recognition ◽  
Language Processing ◽  
Computational Cost ◽  
Sequential Learning ◽  
High Quality ◽  
Fast Training ◽  
Online Sequential Learning ◽  
And Performance ◽  
Resource Constrained Devices ◽  
Constrained Devices

Emotion recognition, among other natural language processing tasks, has greatly benefited from the use of large transformer models. Deploying these models on resource-constrained devices, however, is a major challenge due to their computational cost. In this paper, we show that the combination of large transformers, as high-quality feature extractors, and simple hardware-friendly classifiers based on linear separators can achieve competitive performance while allowing real-time inference and fast training. Various solutions including batch and Online Sequential Learning are analyzed. Additionally, our experiments show that latency and performance can be further improved via dimensionality reduction and pre-training, respectively. The resulting system is implemented on two types of edge device, namely an edge accelerator and two smartphones.

scholarly journals Computing Expectiles Using k-Nearest Neighbours Approach

Symmetry ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 645
Author(s):  
Muhammad Farooq ◽  
Sehrish Sarfraz ◽  
Christophe Chesneau ◽  
Mahmood Ul Hassan ◽  
Muhammad Ali Raza ◽  
...  
Keyword(s):  
Computational Cost ◽  
Real Life ◽  
Distance Measures ◽  
Computational Time ◽  
High Dimensional ◽  
Test Error ◽  
Nearest Neighbours ◽  
Comparable Performance ◽  
Asymmetric Least Squares ◽  
Low Computational Cost

Expectiles have gained considerable attention in recent years due to wide applications in many areas. In this study, the k-nearest neighbours approach, together with the asymmetric least squares loss function, called ex-kNN, is proposed for computing expectiles. Firstly, the effect of various distance measures on ex-kNN in terms of test error and computational time is evaluated. It is found that Canberra, Lorentzian, and Soergel distance measures lead to minimum test error, whereas Euclidean, Canberra, and Average of (L1,L∞) lead to a low computational cost. Secondly, the performance of ex-kNN is compared with existing packages er-boost and ex-svm for computing expectiles that are based on nine real life examples. Depending on the nature of data, the ex-kNN showed two to 10 times better performance than er-boost and comparable performance with ex-svm regarding test error. Computationally, the ex-kNN is found two to five times faster than ex-svm and much faster than er-boost, particularly, in the case of high dimensional data.

scholarly journals Control system of 4-DOF palletizing robot based on improved R control multi-objective trajectory planning

2021 ◽  
Vol 13 (4) ◽  
pp. 168781402110027
Author(s):  
Jianqiang Wang ◽  
Yanmin Zhang ◽  
Xintong Liu
Keyword(s):  
Control System ◽  
Trajectory Planning ◽  
Robot Control ◽  
Machining Process ◽  
Planning System ◽  
Positioning Accuracy ◽  
Multi Objective ◽  
Planning Algorithm ◽  
Function Testing ◽  
Robot Control System

To realize efficient palletizing robot trajectory planning and ensure ultimate robot control system universality and extensibility, the B-spline trajectory planning algorithm is used to establish a palletizing robot control system and the system is tested and analyzed. Simultaneously, to improve trajectory planning speeds, R control trajectory planning is used. Through improved algorithm design, a trajectory interpolation algorithm is established. The robot control system is based on R-dominated multi-objective trajectory planning. System stack function testing and system accuracy testing are conducted in a production environment. During palletizing function testing, the system’s single-step code packet time is stable at approximately 5.8 s and the average evolutionary algebra for each layer ranges between 32.49 and 45.66, which can save trajectory planning time. During system accuracy testing, the palletizing robot system’s repeated positioning accuracy is tested. The repeated positioning accuracy error is currently 10−1 mm and is mainly caused by friction and the machining process. By studying the control system of a four-degrees-of-freedom (4-DOF) palletizing robot based on the trajectory planning algorithm, the design predictions and effects are realized, thus providing a reference for more efficient future palletizing robot design. Although the working process still has some shortcomings, the research has major practical significance.

Sign in / Sign up

Export Citation Format

Share Document