Warehouse Robot Research Articles

Adaptive path finding algorithm in dynamic environment for warehouse robot

Warehouse robots have been widely used by manufacturers and online retailer to automate good delivery process. One of the fundamental components when designing a warehouse robot is path finding algorithm. In the past, many path finding algorithms had been proposed to identify the optimal path and improve the efficiency in different conditions. For example, A* path finding algorithm is developed to obtain the shortest path, while D* obtains a complete coverage path from source to destination. Although these algorithms improved the efficiency in path finding, dynamic obstacle that may exist in warehouse environment was not considered. This paper presents AD* algorithm, a path finding algorithm that works in dynamic environment for warehouse robot. AD* algorithm is able to detect not only static obstacle but also dynamic obstacles while operating in warehouse environment. In dynamic obstacle path prediction, image of the warehouse environment is processed to identify and track obstacles in the path. The image is pre-processed using perspective transformation, dilation and erosion. Once obstacle has been identified using background subtraction, the server will track and predict future path of the dynamic object to avoid the obstacle.

Cognitive and artificial intelligence system for logistics industry

Artificial intelligence is an important branch of cognitive science. Artificial intelligence has been applied to medical, education, logistics and other industries, which has broad prospects for development. Hotel logistics industry uses artificial intelligence technology to complete intelligent search, face recognition, combined with large data calculation and planning reasonable path in warehousing. Taking China's hotel logistics industry as the research object, this paper analyses the application of artificial intelligence technology in the logistics industry. In the warehousing process, artificial intelligence technologies including compile storage code, automatic picking with automated guided vehicle, warehouse robot to improve work efficiency. Logistics distribution links use artificial intelligence technology to plan the best path, improve the recognition rate of express waybill that save a lot of labour. Artificial intelligence technology allocates logistics resources, optimises logistics links, and improves logistics efficiency and other measures to promote the development of logistics informatisation and automation.

Design and implementation A* Algorithm on movement system robot in the warehouse

The advancements in warehouse robotics at this current moment is considered as a trending topic. There is an abundance of multinational electronic companies that requires the use of robots in the field, especially warehouse robots that can be used to send and receive items efficiently. The width of warehouses with many branching routes creates problems for the movements of these robots. An example of said problem would be the inability to move efficiently using the nearest route possible. Therein lies the need for an algorithm that may solve these issues. This research proves that the use of A* Algorithm can be implemented for warehouse robot tracks which involves the usage of visible light communication method. The routes used for experimentation have specialized schematics in the form of a grid. In these experiments using a track with 2x2 and 3x3 schematics presents a success ratio of about 56,6% to 66,6% with an estimate distance calculation error between a minimum of 1cm and maximum of 20 cm. With the implementation of A* Search Algorithm, the robot could determine the shortest route in which it could efficiently move less steps compared to robots which uses all possibilities that exists.

Productivity Improvement of a Eco Friendly Warehouse using Multi Objective Optimal Robot Trajectory Planning

Production of environment is one of the top rated objectives of all countries. 10% emission of CO2 in the world is from logistics industries due to freight transports and warehousing operations. Green logistics is an important step to minimise ecological impacts of the logistics operations. Green environment in a warehouse plays a mandatory role in green logistics. Automation, robotics and smart systems give a good contribution in making the warehouse environment clean and green. A method for productivity improvement of a green warehouse using multi objective optimal trajectory planning of a warehouse robot is proposed in this paper. Mixed load palletising operation (build-to-order palletising) is considered. Two multi objective optimisation algorithms such as multi objective particle swarm optimisation (MOPSO) and multi objective differential evolution (MODE) are used. A numerical example on an Industrial robot (MTAB ARISTO 6XT robot) is presented. An economic and productivity analysis is carried out. The obtained results proved that the multi objective optimisation on warehouse robot trajectory planning enhances supply chain productivity and profits.

Activation and Spreading Sequence for Spreading Activation Policy Selection Method in Transfer Reinforcement Learning

This paper proposes an automatic policy selection method using spreading activation theory based on psychological theory for transfer learning in reinforcement learning. Intel-ligent robot systems have recently been studied for practical applications such as home robot, communication robot, and warehouse robot. Learning algorithms are key to building useful robot systems important. For example, a robot can explore for optimal policy with trial and error using reinforcement learning. Moreover, transfer learning enables reuse of prior policy and is effective for environment adaptability. However, humans de-termine applicable methods in transfer learning. Policy selection method has been proposed for transfer learning in reinforcement learning using spreading activation model proposed in cognitive psychology. In this paper, novel activation function and spreading sequence is discussed for spreading policy selection method. Fur-ther computer simulations are used to examine the effectiveness of the proposed method for automatic policy selection in simplified shortest-path problem.

Optimal autonomous mobile robot motion planning for green logistics

In 2017, CO2 emissions from logistics activities is 0.82 million tons across the world. Introduction of low exhaust emission vehicles, reduction in transportation distance, introduction of electrical vehicles, improvement in load factor, reduction in cost, fast delivery are goals of green logistics. To accomplish these goals, Autonomous mobile robots are good choice. This paper proposes a good method for improving the performance of a warehouse robot by a multi objective optimal motion planning. Wheeled mobile robot is considered. Two multi objective optimisation algorithms [elitist non-dominated sorting genetic algorithm (NSGA-II) and multi objective differential evolution (MODE)] are used. A cubic NURBS curve constructs the robot path. Four multi objective performance metrics and two methods are utilised to examine the performance of MODE and NSGA-II algorithms. The results from a numerical simulation proved that the suggested method is a good idea to improve the green warehouse operations and to do necessary automation.

Optimal autonomous mobile robot motion planning for green logistics

In 2017, CO2 emissions from logistics activities is 0.82 million tons across the world. Introduction of low exhaust emission vehicles, reduction in transportation distance, introduction of electrical vehicles, improvement in load factor, reduction in cost, fast delivery are goals of green logistics. To accomplish these goals, Autonomous mobile robots are good choice. This paper proposes a good method for improving the performance of a warehouse robot by a multi objective optimal motion planning. Wheeled mobile robot is considered. Two multi objective optimisation algorithms [elitist non-dominated sorting genetic algorithm (NSGA-II) and multi objective differential evolution (MODE)] are used. A cubic NURBS curve constructs the robot path. Four multi objective performance metrics and two methods are utilised to examine the performance of MODE and NSGA-II algorithms. The results from a numerical simulation proved that the suggested method is a good idea to improve the green warehouse operations and to do necessary automation.

AI buzzwords explained

Kiva Systems was founded in 2003 to develop robot technology that automates the fetching of goods in order-fulfillment centers. It was acquired by Amazon in 2012 and changed its name to Amazon Robotics in 2014. Amazon order-fulfillment centers have inventory stations on the perimeter of the warehouse and storage locations in its center, see Figure 1 . Each storage location can store one inventory pod. Each inventory pod holds one or more kinds of goods. A large number of warehouse robots operate autonomously in the warehouse. Each warehouse robot is able to pick up, carry and put down one inventory pod at a time. The warehouse robots move inventory pods from their storage locations to the inventory stations where the needed goods are removed from the inventory pods (to be boxed and eventually shipped to customers) and then back to the same or different empty storage locations ( Wurman, D'Andrea, & Mountz, 2008 ). 1

Study on electric energy consumed in intermittent series–parallel elastic actuators (iSPEA)

On compliant actuators, intermittent series–parallel elastic actuators (iSPEA) can reduce motor load by variable load cancellation through recruitment of parallel springs by a single motor. However, the potential to reduce electric energy consumed, compared to a traditional stiff driven joint has not yet been evaluated thoroughly both in simulations and experiments. We have developed a 1DOF MACCEPA-based iSPEA test bench with a self-closing intermittent mechanism. An iSPEA driven warehouse robot is used as a case study in simulation. A method to compare iSPEA and traditional actuators is proposed. This paper shows a match between our simulations and experimental results regarding electric energy consumed. Although the chosen gear ratio shows to be detrimental for both the stiff actuator and the iSPEA, the electric energy consumed by the iSPEA is about 25% to 67% of the stiff actuator, for a warehouse robot placing 3 objects on a shelf.

Stacking Storage Scheduling Optimization for Profile Automated Warehouse Robot Based on Mixing-degree

Stacking storage structure has to be used in profile automated warehouse, which results that the above ones of a rack must to be removed before the rack moving. So the delay of the procedure increases. Aiming at the problem, we firstly defined the mixing-degree of the whole stacking-storage as an important indicator of warehouse wholeness, which can characterize warehouse long-term efficiency. Secondly, a utility function was built to describe the measurement of warehouse status based on the mixing-degree. Finally a scheduling optimization model on constraints of the initialization condition was proposed, with always calculating the warehouse mixing-degree and top statuses. Simulation and field experiment on real Nanping AL. Robots system shows that the proposed algorithm achieves good performance and efficiency in long-term, though no optimization in short-term, which roots from less average expectation of the top-racks moves.

Growth in e-commerce boosts innovation in the warehouse robot market

Purpose This paper aims to illustrate how the growth in e-commerce has catalysed innovative developments in robots for use in warehouses. Design/methodology/approach Following a brief introduction to e-commerce and warehouse robots, this first paper discusses Amazon’s involvement with robotic technology. It then considers the community of recently founded companies manufacturing warehouse robots, together with details of their products. The paper concludes with a short discussion. Findings Amazon pioneered the use of robotics in its e-commerce warehouses with Kiva robots. It acquired the company in 2012, renaming it Amazon Robotics, and withdrew the products from open sale, triggering a boom in development activity to fill the gap in the market. Many companies in the USA, Europe and Asia have since been set up to exploit this opportunity and now manufacture robots for use in fulfilment centres around the world. While several products resemble the Kiva robots, others are more sophisticated and feature capabilities such as shelf picking and autonomous navigation. In the longer term, it is anticipated that functions such as product packing will also be conducted by robots, leading to fully automated fulfilment centres. Originality/value This paper discusses the recent and dramatic upsurge in the development of robots for use in warehouses, particularly those serving the rapidly growing e-commerce sector.

SWARM ROBOTICS FOR INTELLIGENT WAREHOUSING: AN APPLICATION

Warehousing has become an important part of the sup ply chain of any business. With a rise in global bu siness there is increasing pressure to modernize and improve the critical comp onent of warehousing. This paper proposes automatio n of warehousing by using swarm intelligence. It describes the various key fe atures that define a swarm of robots, the various c ontrol mechanism. This paper proposes a sample design of the warehouse robot and the warehouse layout. It proposes some key infrast ructural changes in order to enable swarm intelligence. It proposes a model and unique control mechanism between the various stakeh olders of the warehousing system. It also demonstrates improvements in some a reas such as effective utilization of space, reduct ion in retrieval time, reduction in power consumption and overall improvement in effici ency.