TRAFFIC PATH PLANNING AND MANAGEMENT FOR ROBOT ARM MOVEMENTS

Abstract

The invention relates to a method comprising calculating a trajectory curve, with a planning, sequencing, and trajectory curve path manager in combination with an information acquisition module that utilizes an image generation system, using spline interpolation and fitting low-degree polynomials between two adjacent waypoints from an initial state to a final state through one or more intermediate waypoints; updating the trajectory curve in a database in the computing system or in the cloud, for fast retrieval of trajectory curve paths and fast processing of objects in a robot arm-controlled environment, according to kinematic and dynamic limits of the automated system, to obtain a final trajectory curve;and actuation of the robot arm from an initial state through one or more intermediate waypoints to a final state according to the final trajectory curve, as transmitted by the robot controller. The invention also relates to a system comprising an automated machine that utilizes a robot and is operated by a robot control system configured for automatic, repetitive, and non-repetitive movement.

Description

Summary

[0001] The present invention relates to a trajectory generation method for moving a robot arm along the fastest and smoothest trajectory, avoiding obstacles and jerky movements, in the shortest possible time to predetermined endpoints. This method involves implementing a planning, sequencing, and trajectory manager to pre-plan the movements and simultaneously create a database of trajectories that is subsequently used to store and retrieve repetitive movements of the robot arm, resulting in time savings and smooth movements. In a dynamically changing operating environment, endpoints are calculated by implementing an information retrieval module that captures a three-dimensional image of the processing area and predicts a 3D pose, which is then translated into position coordinates for use by the robot to move to the target endpoint.The Planning Manager works synchronously with the Information Acquisition Module, and the Sequence Manager provides a highly conducive environment for moving objects smoothly with controlled speed, seamlessly, and efficiently, mimicking human movement. Field of the invention

[0002] The present invention relates to a method for generating and storing trajectories for a smooth and shortest path movement of a robot arm using a planning, sequencing, and trajectory manager in conjunction with an information retrieval module. The present invention also provides parallel processing of trajectories of future robot arm movements to minimize labor time, resulting in increased speed of the manufacturing process.

[0003] DE102022133123A1 describes a technique for training a neural network, comprising generating a plurality of input vectors based on a first plurality of task demonstrations associated with a first robot performing a first task in a simulated environment, wherein each input vector included in the plurality of input vectors specifies a sequence of poses of an end effector of the first robot, and training the neural network to generate a plurality of output vectors based on the plurality of input vectors.Also described is another technique for generating a task demonstration, comprising generating a simulated environment including a robot and at least one object, causing the robot to at least partially perform a task associated with the at least one object within the simulated environment based on a first output vector generated by a trained neural network, and recording demonstration data of the robot at least partially performing the task within the simulated environment.

[0004] DE 10 2021 204 961 B4 describes a method for controlling a robot device, comprising: providing demonstrations for a robot skill, each demonstration demonstrating a trajectory comprising a sequence of robot configurations, each robot configuration being described by an element of a predetermined configuration space having the structure of a Riemannian manifold; determining, for each demonstrated trajectory, a representation of the trajectory as a vector of weights of predetermined basic movements of the robot device by searching for a vector of weights that minimizes a distance measure between the combination of the basic movements according to the vector of weights and the demonstrated trajectory, the combination being mapped to the manifold;Determining a probability distribution of the weight vectors by fitting a probability distribution to the weight vectors determined for the demonstrated trajectories; and controlling the robot device by performing basic movements according to the determined probability distribution of weight vectors.

[0005] DE102020212658A1 describes an apparatus and a method for controlling a robot device, the method comprising: training a control model comprising a parameter model and an object model, the training comprising: for each initial state-target state pair of a plurality of initial state-target state pairs, providing a control state sequence comprising states and state transitions, each state transition being associated with a set of task parameters; determining a set of state transition-state-state transition triples contained in the provided control state sequences;for each state transition-state-state transition triple: adapting the parameter model such that the parameter model determines a probability distribution for each task parameter from the set of task parameters associated with the state transition following the state, adapting the object model such that the object model determines a probability distribution for the state of the object for each object of the one or more objects; and controlling the robot device with the control model using the trained parameter model and the trained object model.;

[0006] DE102019122790B4 describes a system comprising: an articulated robot with a manipulator; one or more processors; and memory storing executable instructions that, when executed by the one or more processors, cause the system to at least: obtain an image from a camera, the camera positioned so that the view of the camera is directed along the axis of the manipulator towards an object to be grasped; provide the image and a suggested action to a trained neural network to generate a Q-value from a value function that is used to select an action most likely to produce a desired grasp, and move the manipulator based on the Q-value to grasp the object with the manipulator when the Q-value reaches a threshold.

[0007] DE102018203078B3 describes a method for automatically generating a movement trajectory of a reference point of a machine to be controlled automatically, wherein the machine has drives which are designed to move the reference point of the machine in space, specifically controlled by a control device which is designed to control the drives of the machine on the basis of the automatically generated movement trajectory as a reference variable by means of a movement controller, wherein the movement trajectory is automatically generated on the basis of at least one first movement instruction to be executed in a blending mode and at least one second movement instruction following the first movement instruction of a machine movement program executed by the control device by means of a path planning program. General state of the art

[0008] In an industrial environment, a trajectory is taught by a human expert and later replayed in a typical teach-and-playback manufacturing environment. A trajectory, or path, connects two or more waypoints, resulting in one or more trajectories per robot arm. Each waypoint is typically trained by a human operator based on the poses or positions used when picking up and placing an object.

[0009] According to a conventional method, an operator prepares a robot arm through trial and error by establishing waypoints that meet conditions to prevent the robot arm from entering the inoperable area or interfering with peripheral devices or other waypoints. In certain situations, a robot's trajectory path that allows the robot arm to operate at an optimal speed may not be generated quickly enough, resulting in an increase in tactile time. In such a case, manual intervention is required to revisit and reset the robot arm's learned waypoints to achieve an optimal tactile time.

[0010] In another conventional method, an operator can prepare the robot arm by teaching it two or more waypoints that may require sharp turns or changes in direction. This results in the arm generating trajectories with sudden acceleration or deceleration of movements. This can affect the picking and placing operations due to the vibrations generated by such robot arm movements. The risk of disrupting the manufacturing environment is high, resulting in inefficient operation, increased cycle time, and a substandard final product.

[0011] Playback robot arms are typically designed such that a robot controller teaches a robot arm a plurality of waypoints for one end of a robot arm (manipulator); these waypoints may include (but are not limited to) a starting point, an ending point, and intermediate points. A robot hand is suitably integrated into one end of the manipulator. The robot controller is programmed to perform interpolation at the taught or trained command points to determine a trajectory path that passes through the waypoints. The robot controller is then programmed to move the robot arm smoothly along the specified trajectory path.While this may work in most environments, the robot arm is likely to encounter collisions with certain obstacles or a dynamically changing environment, where waypoints may move according to the task being performed and the object being manipulated.

[0012] The generation of trajectory paths aims at generating motion control paths of robot arms that ensure that the planned trajectory is executed smoothly without any destabilizing jerky movements, and on which the distance is covered in the shortest possible time without colliding with any of the waypoints around the work area.

[0013] What's needed is sophisticated trajectory generation along with a planning manager to implement a predictive strategy for executing a movement along a specific trajectory without increasing the time required, and one that can incorporate trajectories planned well in advance to make the robot arm faster. Defining a robot arm trajectory that takes into account obstacle avoidance, traversing a complicated maze, and, in some complex cases, dynamically changing waypoints by implementing an information retrieval module ensures more efficient, safer, and faster operation.During the definition and advance planning of trajectories, many laws of mechanical motion must be considered, such as trajectory velocity and acceleration saturation limits of the motor drives, and resonance points of the actuator structure when using electric / hydraulic or pneumatic drive modes, to arrive at a smooth trajectory path in practical implementations. A trajectory path involves determining a path using multiple waypoints through which the path guidance is planned to avoid collisions and determine the shortest route. The trajectory is then used by the robot controller to move the robot arm along the planned trajectory path.The trajectory uses the geometric path planned for a specific task to determine the path velocity and acceleration around each waypoint, depending on the pivot angle, to minimize the effects of resonance and smooth the robot arm's movement. In a simple industrial machine, a trajectory is typically trained by a human operator through trial and error. However, as machines become more complex and their capabilities increase, it becomes increasingly necessary to incorporate automated trajectory planning methods, for which a trajectory planning manager alone may not be sufficient.In such cases, an imaging-based device and method, combined with an information retrieval module, are required to dynamically plan the trajectories using forward-looking algorithms and pre-stored trajectories. In cases where the robot's environment has changed, it is essential that the new trajectory be quickly calculated and communicated to the robot controller to ensure rapid execution. Furthermore, by incorporating artificial intelligence and machine learning techniques, all frequently used trajectories relevant to a specific product type are stored in databases to minimize machine configuration setup during product changeovers. These methods have therefore evolved from an option to a true necessity in robot-controlled industrial environments.

[0014] In certain cases, trajectory planning algorithms have limitations that can sometimes make it impossible to plan the robot arm's movement from one waypoint to another on a single trajectory due to obstacle avoidance. In such cases, it is essential to plan multiple trajectories while handling an object if the robot arm must carefully maneuver around the obstruction. In this case, two or more intermediate points must be added between two waypoints, thus requiring the planning and combination of multiple trajectories to reach a target position. This results in the start / stop movements typical of a robot traversing multiple trajectories, with multiple deceleration and acceleration movements for each trajectory, resulting in vibrations due to the resonance characteristics involved. Summary of the invention

[0015] Against this background, an object of one aspect of the present invention is to provide a trajectory path planning manager for the motion control device using a planning manager in conjunction with a sequence manager for practical standard applications where the waypoints do not change.

[0016] Another object of one aspect of the present invention is to provide a trajectory planning manager for the motion control device for a dynamically changing environment where the waypoints may change, by supplementing the planning and sequencing manager with an information retrieval module for capturing an image and providing a map for the trajectory management module. The information retrieval module helps manage complex situations commonly encountered in applications involving multiple robot arms or obstructions.Using the work template map provided by the information acquisition module, the trajectory management module generates the waypoints along the desired trajectory using a class of polynomial interpolation or spline interpolation to arrive at a time-based control sequence to smoothly move the robot arm from its current position to the target. The trajectory management module handles exponential complexity in terms of the degrees of freedom (the controllable joints) of a given robot by applying artificial intelligence followed by machine learning techniques.The trajectory path manager further includes means for calculating from the spline interpolation implementation that produces smooth movement between multiple path segments without position, path velocity, and acceleration discontinuities, and for avoiding the Runge phenomenon that causes oscillation or gyration at the beginning or end of the robot arm movement, which is typical of polynomial interpolation implementations when working with equidistant waypoints.

[0017] According to another aspect of the present invention, a method for determining a single move is provided by implementing a chain motion mode in which multiple trajectories are planned together and then combined into a single one. This reduces pauses between two trajectories because the robot arm does not have to wait for the next trajectory to be planned for each individual segment on the multi-segment path. When merging multiple trajectories, it is normal for some delay to occur during the transition between multiple trajectories due to deceleration and acceleration at each intermediate waypoint, especially when the planned trajectories require an abrupt change of direction.To overcome this problem, a blending concept for the trajectories with a smooth curvature is implemented. Instead of reaching the intermediate waypoint, a blending radius is calculated for the merging with the path of the next trajectory to effectively reduce or minimize the effect of sudden deceleration and acceleration. The blending is controlled by a fillet radius parameter that determines the degree of curvature needed to smooth the path near the transition. This makes the movement as smooth as a human's.

[0018] According to a further aspect of the present invention, a method is provided in which the planning manager plans trajectories between all known waypoints in advance, so that when a sequence of trajectories needs to be executed, the robot controller retrieves the trajectory from the planning manager without any waiting time, since the trajectories have been pre-planned and pre-stored. If no pre-planned and stored trajectories are available for a set of waypoints, the planning manager, together with the sequence manager, determines the trajectory from the initial state to the nearest intermediate point where pre-planned trajectories exist, resulting in a significant time reduction compared to cases where no pre-planned trajectories are available.The same logic is executed if no pre-stored trajectories exist up to the final state, in which case a new trajectory is determined from the nearest waypoint to the final state. The flexibility of the pre-stored trajectory database is increased, making it more efficient and faster.

[0019] According to another aspect of the present invention, a method is provided in which a 3D (three-dimensional) image of the work environment is acquired by the information acquisition module, which predicts a 3D pose or map to determine the coordinates of all waypoints and obstacles to guide the robot arm to a specific endpoint based on the instruction received from the robot controller. Furthermore, additional parameters such as rotation coordinates for row, pitch, and yaw are determined based on the 3D map, resulting in a 6D (six-dimensional) calculation of the trajectory path to move the robot arm from the initial to the final state.

[0020] According to another aspect of the present invention, a method is provided wherein the information retrieval manager manages a pipeline of imaging server actions to determine object locations and to communicate the non-linear sequence of trajectories to the robot controller in real time.

[0021] According to another aspect of the present invention, a method is provided for rapidly calculating motion trajectories for automated systems such as robots, cranes, and vehicles. Given a set of waypoints and their associated obstacles and constraints, one or more initial robot states, and one or more desired final robot states, the method begins with a novel iterative process to calculate a sample motion trajectory that is fast and achieves the desired robot state. Each iteration improves the trajectory by implementing PID (Proportional-Integral-Derivative), MFC (Model Predictive Control), and adaptive control algorithms to make the robot arm's motion faster and smoother until it meets all criteria for desired acceleration and path velocity tolerances with respect to the payload.Offline (before execution), this flow is used to generate multiple trajectories for multiple initial and final states of the robot, and then apply artificial intelligence and machine learning techniques to create a database of all frequently used trajectories. This process enables rapid responses to commands to move the robot arm from one state to another, as the database has most of the trajectories pre-calculated and stored in advance. With a further implementation of deep learning techniques, the robot processes and motion are stored and optionally refined through a frequent calculation that includes various input and output states of the robot.

[0022] Because the planning and sequence managers work together with the information retrieval module, most trajectories are ready for processing with minimal computation time. This process of manipulating a visually guided robot arm with complex balance trajectories is fast, seamless, and smooth, mimicking human movement. Brief description of the drawings

[0023] The present disclosure will become clearer upon reading the following description of non-limiting embodiments with reference to the accompanying drawings: Fig. Figure 1 shows a block diagram of a computing system comprising the various subsystems involved, which determines an optimized trajectory path to issue commands to the robot controller to move the respective robot arm. Fig. 2 shows a flowchart illustrating trajectory motion planning for a robot arm with predetermined waypoints according to one embodiment. Fig. 3 shows a flowchart illustrating trajectory motion planning of a robot arm with predetermined and dynamic waypoints according to one embodiment. Fig. 4 shows a flowchart of sequence A according to one embodiment, wherein the information acquisition manager predicts the 3D waypoints, calculates the roll, pitch and yaw rotation coordinates, resulting in a six-dimensional trajectory trajectory of the workspace. Fig. Figure 5 shows an example of a trajectory curve between six waypoints using spline interpolation. Detailed description of the drawings

[0024] The following description concerns the calculation of motion trajectories for automated systems, which takes into account a payload and the balance of the robot while avoiding obstacles, which reduces stresses to minimize wear on the mechanics involved, in order to produce a nimble and smooth movement from an initial position to a final position.

[0025] In one embodiment of the present disclosure, the system and methods provided herein are used to accelerate and improve the movement of a robot for loading and unloading contact lens blister packs from an infeed loader to the inspection station in an automated facility. In this case, the set of initial states is defined by a desired position of a suction cup or pick-up end-effector integrated into the robot for lifting the blister pack. The set of final states is defined by a position of the pick-up end-effector at the inspection station, where intelligent imaging performs precise fine positioning and then deactivates the end-effector suction cup holding the contact lens blister pack, resulting in unloading at the inspection station.A high degree of positional accuracy in the X, Y, and Z axes and the orientation in the final state of unloading the contact lens blister pack is maintained. To increase system throughput and reduce robot wear, the goal is to quickly calculate a motion trajectory curve from one of the initial states to one of the final states, avoiding both stationary and dynamically moving obstacles, using a chain mode concept. The chain mode is implemented by the planning manager by concatenating multiple trajectories and adopting smooth motions for trajectory velocity and acceleration to ensure vibration- and jerk-free movement through all given waypoints.

[0026] It will be Fig. 1, where block diagram 50 is shown as an example of a computing system 52 for smooth and vibration-free motion planning according to one embodiment. The computing system 52 includes a sequence planning subsystem 106, a path planning subsystem 108, and a trajectory planning subsystem 110, suitably linked to a database and communicatively coupled to a robot controller 104 for controlling a robot arm 102 or other system configured for autonomous motion within the automated machine 112. Although the computing system 52 is depicted as separate from the robot controller 104, it should be understood that, in some examples, one or more components of the computing system 52 may be integrated with the robot controller 104 or may be a standalone module for actuating the robot arm 102.The computing components can include artificial intelligence, machine learning, reinforced learning, and deep learning algorithms, among others, to build a powerful and efficient database of trajectories that are always available, rather than calculating the trajectories in real time when a waypoint map is received from the computing system. The database serves as a trajectory storage subsystem that is always available and adaptable to various configurations of industrial machines used for processing and manufacturing different products.

[0027] It will be Fig. 2, where the flowchart 100 schematically illustrates operations to be performed by the robot controller. The flowchart 100 shows the interaction between the various modules within the computing system 52 of Fig. 1. The flow chart is specifically designed for automated machines, with the planned curve paths based on a predefined set of waypoints. This is adaptable to automated machines such as those used for packaging, sorting, or labeling processed products, where most of the processing points for the products are fixed.

[0028] The process typically begins with the input command 116 to the robot controller. The robot controller then transmits the waypoints (starting waypoint and ending waypoint) to the database 110 of planned trajectories. The database, in turn, sends the desired trajectory to the robot controller if the pre-planned or specified trajectory exists for these waypoints. Subsequently, the robot controller 104 controls the robot arm 102 to the final destination waypoint at the specified speed of movement, path velocity, and trajectory.However, in a case where a predefined trajectory is missing or unavailable, the robot controller 104 obtains information about the absence of a predefined trajectory from the planned trajectory database 110, followed by a command to start the process of planning a new trajectory from the robot controller 104 to the sequence manager 106. The sequence manager 106 further checks the waypoint positions and decides on the sequence of trajectories to be executed after implementing a blending of trajectories with all intermediate waypoints, taking into account the fillet radius parameter, which determines the degree of curvature necessary to smooth the trajectory near the transition from one waypoint to the next.The calculated sequence is then transmitted to the trajectory manager 108, which determines the fastest trajectory path to the final destination waypoint and uploads the information to the planned trajectory path database 110 for storage and transmission to the robot controller 104, which in turn executes the movement of the robot arm 102. The executed movement results in a movement as smooth as a human movement.

[0029] In Fig. 3, the flowchart 130 schematically illustrates operations to be performed by the robot controller when dealing with dynamic waypoints. The flowchart 130 shows the interaction between the various modules within the computing system 52 of Fig. 1, where the planned trajectories are based on both varying and fixed sets of waypoints. This is applicable to automated machines where interaction between multiple processing points is involved, resulting in unpredictable environments and changing conditions. The complexity of such operations requires a series of pre-planned motion sequences, on-the-fly trajectory calculations, and the ability of the trajectory manager to quickly adjust the sequences and trajectories to achieve smooth and precise operation of the robot arm.

[0030] The flow chart in Fig. 3 begins with the input command 116 to the robot controller. The robot controller 104 then transmits the waypoints (start, intermediate, and end waypoints) to the database 110 of planned trajectories. The database, in turn, sends the desired trajectory to the robot controller if the pre-planned or pre-determined trajectory exists for these waypoints. Subsequently, the robot controller 104 controls the robot arm 102 to the final destination waypoint at the specified speed of movement, path velocity, and curvature. However, in the event that a pre-determined trajectory is missing or unavailable, or if there are obstacles in the pre-planned trajectories, the robot controller 104 sends a command to the sequence manager 106 to begin the process of planning the new trajectory.The sequence manager 106 checks the waypoint positions, including obstacles and intermediate waypoints. This information is transferred to the planning manager 108. The planning manager, recognizing the recently changed environment, sends a request to a branch 112 (A). The trajectory manager determines the trajectory by implementing PID (Proportional-Integral-Derivative), MFC (Model Predictive Control), and adaptive control algorithms to ensure smooth and resonance-free movement from an initial state or initial waypoint to a final state or final waypoint of the robot arm through all intermediate waypoints. Furthermore, the calculated trajectory is uploaded to 116 for further characterization of the trajectory using artificial intelligence, machine learning, and reinforcement learning, and is then stored in the database 110 located in the computing system 52 of [the original text]. Fig. 1 or in the cloud. The database 110 is iteratively refined and updated to ensure that the robot arm can be operated using the pre-planned trajectories with minimal delays for a specific command.

[0031] In Fig. 4, flowchart A begins with the information acquisition manager 195 sending commands to acquire a 3D pose of the work environment to the image generation system in step 200. In step 205, the software algorithm identifies and calculates the rotation values ​​related to roll, pitch, and yaw, and then returns a total of six values ​​in step 210, namely the X, Y, and Z coordinates of the current state of waypoint locations, which may contain obstacles, and intermediate waypoint locations, along with the determined values ​​for roll, pitch, and yaw. In step 210, a trajectory path is generated. Furthermore, parameters such as rotation coordinates, such as roll, pitch, and yaw, are determined taking into account all waypoints, the initial state, and the final state in 205 to determine the trajectory path in 210. In the next step, the six-dimensional trajectory path is sent in 210 to the path manager 107 in Fig. 3 and the process is then terminated in 220.

[0032] In Fig. Figure 5 shows an example of a trajectory path calculated using spline interpolation between six waypoints P0-P6. Spline interpolation fits low-order polynomials between two adjacent waypoints, for example, by fitting five cubic or sliced ​​polynomials between each two of six waypoints, instead of fitting a single six-order polynomial. This minimizes the interpolation error and also eliminates problems associated with oscillation (vibration), resulting in smooth movement of the robot arm. In diagram 300 of Fig.Figure 5 shows six waypoints, namely P0, P1, P2, P3, and P6, as an example. C1-C5 are the resulting curves that were merged to form a spline path between each pair of waypoints. It can be seen that the robot controller follows the trajectory curve path from C1 to C5 to execute a movement from its initial state P0 to its final state P6. The mathematical formulas or analysis of acceleration, deceleration, and peak path velocity between waypoints will not be discussed, as they are outside the scope of the invention.

[0033] It should be understood that various modifications not yet described may be made, and each such modification is intended to be covered by the appended claims insofar as it is within the scope of the invention. In this written description, typical cases are used to disclose the invention and also to enable one of ordinary skill in the art to practice the invention, including making and using any devices or systems and implementing any incorporated methods. The patentable scope of the invention is defined by the claims and may include other examples that may occur to one of ordinary skill in the art.

Claims

[1] Method comprising: Calculating a trajectory with a planning, sequencing, and trajectory manager in combination with an information retrieval module using an imaging system, wherein the imaging system is configured to capture a 3D pose of the work environment using spline interpolation and fitting multiple low-order polynomials between two adjacent waypoints from an initial state to a final state through one or more intermediate waypoints; updating the trajectory in a database in a computing system or in a cloud for storage, retrieving the trajectory, and transmitting the trajectory to a robot controller; and operating a robot arm from an initial state through one or more intermediate waypoints to a final state according to the trajectory as transmitted by the robot controller. [2] The method of claim 1, wherein calculating the trajectory comprises calculating a plurality of trajectories for an input command specifying the one or more initial states of the robot arm and the one or more final states of the robot arm with the PID (Proportional-Integral-Derivative), MFC (Model Predictive Control) and adaptive control algorithms, each trajectory of the plurality of trajectories having a different duration and lengths, each trajectory of the trajectories being determined by an initial state of the one or more initial states and an final state of the one or more final states. [3] The method of claim 2, wherein the planning and sequencing manager calculates the plurality of trajectories according to the degrees of freedom affecting the robot arm in the one or more initial states and the one or more final states. [4] The method of claim 2, wherein the planning and sequencing manager calculates the plurality of trajectories in conjunction with the information retrieval module according to the degrees of freedom relating to the robot arm in the one or more initial states and the one or more final states. [5] The method of claim 2, further comprising updating the trajectory path to minimize jerking of the robot arm by repeatedly refining it using artificial intelligence and machine learning in combination with reinforced learning techniques to achieve optimal speed and accuracy over time. [6] The method of claim 2, further comprising updating the trajectories according to respective input states and final states in a database for storage and retrieval. [7] The method of claim 1, wherein the work environment comprises a robot arm mounted on an industrial machine configured for repetitive and non-repetitive motion. [8] The method according to claim 7, wherein a trajectory curve of a repetitive movement is determined from the pre-stored trajectory curve paths located in the database in the computing system or in the cloud. [9] The method of claim 7, wherein a trajectory path of a non-repeating movement is calculated using the 3D positions of all waypoints of the work environment determined by the vision system and by determining the roll, pitch and yaw required for the robot arm to move from an initial state to a final position. [10] A method according to claim 7, wherein, in a case where no trajectory path of a non-repeating movement from a given initial state to a final state is present in the database, the computing system first determines the waypoint closest to the initial state and the waypoint closest to the final state and then determines a trajectory path between these two repetitive waypoints which can be stored in the database. [11] The method of claim 10, wherein the computing system calculates the trajectory to the waypoint closest to the initial state followed by another trajectory from the waypoint closest to the final state to arrive at a complete trajectory from an initial state to the final state, efficiently combining a predetermined trajectory retrieved from the database and a set of calculated trajectories. [12] System comprising: an automated machine that uses a robot and is operated by a robot control system that is configured to perform automatic, repetitive, and non-repetitive motion; the robot controller being configured with software applications that, when executed, cause the controller to: Calculating trajectories from one or more initial states of the working environment to one or more final states using PID (Proportional-Integral-Derivative), MFC (Model Predictive Control), and adaptive control algorithms; wherein each trajectory of the trajectories is determined by means of an initial state of the one or more initial states and a final state of the one or more final states; Updating the trajectories with relevant constraints and limits in a database located in the computing system or in a cloud for subsequent storage and retrieval; and automatically controlling the automated machine from an initial state of the one or more initial states to a final state of the one or more final states according to the trajectory path. [13] The system of claim 12, wherein the controller for calculating the trajectory curve is further configured with algorithms that cause the controller to: Calculating a plurality of trajectories for an input specifying the one or more initial states of the automated machine and the one or more final states of the automated machine, wherein each trajectory of the plurality of trajectories has a different duration, trajectory velocity, acceleration, and curvature; wherein each trajectory of the trajectories is determined by an initial state of the one or more initial states and an final state of the one or more final states. [14] System comprising: an automated machine using a robot and operated by a robot control system incorporating an image generation system and arranged for automatic, repetitive and non-repetitive movement; wherein the robot controller is configured with software applications that, when executed, cause the controller to: Capturing images of a work environment using the imaging system and identifying the waypoints; Calculating trajectories using an information acquisition module and applying PID (Proportional-Integral-Derivative), MFC (Model Predictive Control), and adaptive control algorithms from one or more initial states of the working environment to one or more final states by navigating through the intermediate waypoints; wherein each trajectory of the trajectories is determined by an initial state of the one or more initial states and an final state of the one or more final states. Updating the trajectories with relevant constraints and limits in a database located in a computing system or in a cloud for subsequent storage and retrieval; and automatically controlling the automated machine from an initial state of the one or more initial states to a final state of the one or more final states according to a trajectory of the trajectories.

Images