A review of motion planning algorithms for intelligent robots

Principles of typical motion planning algorithms are investigated and analyzed in this paper. These algorithms include traditional planning algorithms, classical machine learning algorithms, optimal value reinforcement learning, and policy gradient reinforcement learning. Traditional planning algorithms investigated include graph search algorithms, sampling-based algorithms, interpolating curve algorithms, and reaction-based algorithms. Classical machine learning algorithms include multiclass support vector machine, long short-term memory, Monte-Carlo tree search and convolutional neural network. Optimal value reinforcement learning algorithms include Q learning, deep Q-learning network, double deep Q-learning network, dueling deep Q-learning network. Policy gradient algorithms include policy gradient method, actor-critic algorithm, asynchronous advantage actor-critic, advantage actor-critic, deterministic policy gradient, deep deterministic policy gradient, trust region policy optimization and proximal policy optimization. New general criteria are also introduced to evaluate the performance and application of motion planning algorithms by analytical comparisons. The convergence speed and stability of optimal value and policy gradient algorithms are specially analyzed. Future directions are presented analytically according to principles and analytical comparisons of motion planning algorithms. This paper provides researchers with a clear and comprehensive understanding about advantages, disadvantages, relationships, and future of motion planning algorithms in robots, and paves ways for better motion planning algorithms in academia, engineering, and manufacturing.

Uncertain estimation-based motion-planning algorithms for mobile robots

Collision-free motion planning for mobile agents is a challenging task, especially when the robot has to move towards a target position in a dynamic environment. The main aim of this paper is to introduce motion-planning algorithms using the changing uncertainties of the sensor-based data of obstacles. Two main algorithms are presented in this work. The first is based on the well-known velocity obstacle motion-planning method. In this method, collision-free motion must be achieved by the algorithm using a cost-function-based optimisation method. The second algorithm is an extension of the often-used artificial potential field. For this study, it is assumed that some of the obstacle data (e.g. the positions of static obstacles) are already known at the beginning of the algorithm (e.g. from a map of the enviroment), but other information (e.g. the velocity vectors of moving obstacles) must be measured using sensors. The algorithms are tested in simulations and compared in different situations.

Developing a Realistic Simulation Environment for Robotics Harvesting Operations in a Vegetable Greenhouse

Vegetable greenhouse operations are labour intensive. Automating some of these operations can save growers significant costs in an industry with low-profit margins. One of the most demanding operations is harvesting. Harvesting a tomato is a complex operation due to the significant clutter inherent to a greenhouse and the fragility of the object being grasped. Improving grasp and motion planning requires setting up a realistic testbed or testing on-site, which is expensive and time-limited to the growing season and specific environment. As such, it is important to develop a simulation environment to model this operation to help test various strategies before field testing can be conducted. Using the method presented in this work, 3D images are taken from a commercial greenhouse and used to develop a physics-based realistic simulation environment. The environment is then used to simulate a picking operation using various path planning algorithms to investigate the best algorithm to use in this case. The results show that this environment can be used to explore the best approaches to automate harvesting solutions in a vegetable greenhouse environment.

A Survey of Path Planning Algorithms for Mobile Robots

Path planning algorithms are used by mobile robots, unmanned aerial vehicles, and autonomous cars in order to identify safe, efficient, collision-free, and least-cost travel paths from an origin to a destination. Choosing an appropriate path planning algorithm helps to ensure safe and effective point-to-point navigation, and the optimal algorithm depends on the robot geometry as well as the computing constraints, including static/holonomic and dynamic/non-holonomically-constrained systems, and requires a comprehensive understanding of contemporary solutions. The goal of this paper is to help novice practitioners gain an awareness of the classes of path planning algorithms used today and to understand their potential use cases—particularly within automated or unmanned systems. To that end, we provide broad, rather than deep, coverage of key and foundational algorithms, with popular algorithms and variants considered in the context of different robotic systems. The definitions, summaries, and comparisons are relevant to novice robotics engineers and embedded system developers seeking a primer of available algorithms.