SUMMARYThis paper presents a novel solution for precision draping of prepreg composite fabrics onto double curved molds. Our contributions relate to system design, including hardware and software components, and to system integration. On the hardware side, design and implementation of a drape tool with up to 120 suction cups positioned individually by linear actuators are described. On the software side, design and implementation of the software architecture are presented, along with necessary algorithms within sensor technologies and mathematical modeling. The essential system’s components were verified individually, and the entire integrated system was successfully validated in the Proof-of-Concept experiments, performed on an experimental physical model of the system.

Object aligning and holding fixtures for robotic assembly tasks are important in industry in order to successfully complete an assembly. However, the designing of a fixture is usually done manually which can be a long and tedious process including many iterations, even for experienced engineers. This paper presents a method to design fixtures automatically for use in robotic assemblies and pick-and-place tasks. To achieve this a new automated method to design the cut-out for a fixture is introduced. The method uses a parametrized version of the object's imprint to design the cut-out. The fixtures generated using this method are optimized in simulations to determine their final parameters for a specific application. The dynamic simulations are used to evaluate each iteration of the cut-out. Lastly, the method is applied to a use-case from the industry to design a fixture for use in a robotic assembly task.

Vibratory bowl feeders (VBFs) are a widely used option for industrial part feeding, but their design is still largely manual. A subtask of VBF design is determining an optimal parameter set for the passive devices, called traps, which the VBF uses to ensure correct part orientation. This paper proposes a fast and robust strategy for optimising traps, which makes use of dynamic simulation to efficiently evaluate the performance of parameter sets. The optimisation strategy is based on Bayesian Optimisation and selects new parameter sets to evaluate, using a modified Upper Confidence Bound with regression by Kernel Density Estimation as function estimator. The optimisation is run for four different traps with an industrial part and the best parameter sets are tested for robustness in simulation. The traps are then combined to create two sequences performing orientation of the parts and the designs are prototyped and tested on a real VBF.

Achieving both the flexibility and robustness required to advance the use of robotics in small and medium-sized productions is an essential but difficult task. A fundamental problem is making the robot run blindly without additional sensors while still being robust to uncertainties and variations in the assembly processes. In this paper, we address the use of parameterized motions suitable for blind execution and robust to uncertainties in the assembly process. Collisions and incorrect assemblies are detected based on robot motor currents while motion parameters are updated based on Bayesian Optimization utilizing Gaussian Process learning. This allows for motion parameters to be optimized using real world trials which incorporate all uncertainties inherent in the assembly process without requiring advanced robot and sensor setups. The result is a simple and straightforward system which helps the user automatically find robust and uncertainty-tolerant motions. We present experiments for an assembly case showing both detection and learning in the real world and how these combine to a robust robot system.

SUMMARY Programming robotic assembly for industrial small-batch production is challenging; hence, it is vital to increase robustness and reduce development effort in order to achieve flexible robotic automation. A human who has made an assembly error will often simply undo the process until the error is undone and then restart the assembly. Conceptually, robots could do the same. This paper introduces a programming model that enables robot assembly programs to be executed in reverse. We investigate the challenges in running robot programs backwards and present a classification of reversibility characteristics. We demonstrate how temporarily switching the direction of program execution can be an efficient error recovery mechanism. Moreover, we demonstrate additional benefits arising from supporting reversibility in an assembly language, such as increased code reuse and automatically derived disassembly sequences. As a default approach to reversibility, we use program inversion and statement-level inversion of commands, but with a novel override option providing alternative sequences for asymmetric reverse actions. To efficiently program for this model, this paper introduces a new domain-specific language, SCP-RASQ (Simple C++ Reversible Assembly SeQuences). In initial experiments, where 200 consecutive assemblies of two industrial cases were performed, 18 of 22 errors were corrected automatically using only the trial-and-error capabilities that come from reverse execution.

In this work, we present a generic approach to optimize the design of a parametrized robot gripper including both selected gripper mechanism parameters, and parameters of the finger geometry. We suggest six gripper quality indices that indicate different aspects of the performance of a gripper given a CAD model of an object and a task description. These quality indices are then used to learn task-specific finger designs based on dynamic simulation. We demonstrate our gripper optimization on a parallel finger type gripper described by twelve parameters. We furthermore present a parametrization of the grasping task and context, which is essential as an input to the computation of gripper performance. We exemplify important aspects of the indices by looking at their performance on subsets of the parameter space by discussing the decoupling of parameters and show optimization results for two use cases for different task contexts. We provide a qualitative evaluation of the obtained results based on existing design guidelines and our engineering experience. In addition, we show that with our method we achieve superior alignment properties compared to a naive approach with a cutout based on the "inverse of an object". Furthermore, we provide an experimental evaluation of our proposed method by verifying the simulated grasp outcomes through a real-world experiment.

Gripper design is nowadays an area of ongoing research activity. The problem of creating a generic and automated gripper design approach tailored for a specific task is still far from solved. In this paper, we propose a new method of generating finger cut-outs aimed at simplifying the design process of doing so. This method takes root in the idea of using the imprint to produce the finger geometry. We furthermore provide a verification of our newly introduced imprinting method and a comparison to the previously introduced parametrized geometry method. This verification is done through a set of grasping experiments performed in simulation on two objects with geometry features based on those found in industrial setting.

Purpose - For robot motion planning there exists a large number of different algorithms, each appropriate for a certain domain, and the right choice of planner depends on the specific use case. The purpose of this paper is to consider the application of bin picking and benchmark a set of motion planning algorithms to identify which are most suited in the given context.Design/methodology/approach - The paper presents a selection of motion planning algorithms and defines benchmarks based on three different bin-picking scenarios. The evaluation is done based on a fixed set of tasks, which are planned and executed on a real and a simulated robot.Findings - The benchmarking shows a clear difference between the planners and generally indicates that algorithms integrating optimization, despite longer planning time, perform better due to a faster execution.Originality/value - The originality of this work lies in the selected set of planners and the specific choice of application. Most new planners are only compared to existing methods for specific applications chosen to demonstrate the advantages. However, with the specifics of another application, such as bin picking, it is not obvious which planner to choose.

The main contribution of this paper is a method for optimizing the layout of workcells taking into consideration both the reachability of the robot as well as the expected cycle time. To analyse the reachability for systems using sensors to pose estimate objects, the method uses a combination of discrete samples over the space in which objects are located and a manipulability measure based on the determinant of the manipulator Jacobian. To compute the expected cycle time for the robot, the method includes a simulated controller, which is optimized to estimate the performance of the physical robot. For the optimization of the workcell layout the proposed method based on applying Gaussian penalties in local minima is compared to three existing methods for global optimization. For the optimization of the simulated controller three different local methods are compared along with one global.

Vibratory parts feeders with mechanical orienting devices are used extensively in the assembly automation industry. Even so, the design process is based on trial-and-error approaches and is largely manual. In this paper, a methodology is presented for automatic design of this type of feeder. The approach uses dynamic simulation for generating the necessary data for configuring a feeder with a sequence of mechanical orienting devices called traps, with the goal of reorienting all parts from a random to fixed orientation. Then, a fast algorithm for facilitating this configuration task automatically is developed from domain specific knowledge. Finally, the algorithm is validated on three industrial cases and its drawbacks and strengths are discussed in detail.

Doing motion planning for bin-picking with object uncertainties requires either a re-grasp of picked objects or an online sensor system. Using the latter is advantageous in terms of computational time, as no time is wasted doing an extra pick and place action. It does, however, put extra requirements on the motion planner, as the target position may change on-the-fly. This paper solves that problem by using a state adjusting Partial Observable Markov Decision Process, where the state space is modified between runs, to better fit earlier solved problems. The approach relies on a set of waypoints, containing information about which parts of the state space may contain feasible solutions. Waypoints are pushed around the state space by observing which states in the neighborhood lead to successfully solved problems. Two bin-picking scenarios are modeled with the proposed method. One scenario in which the system receives an object pose update while moving towards the place position. Another where the update includes the object type being grasped out of a fixed number of options, each class to be deposited in a different place. When an online POMDP solver is utilized, the state adjusting POMDP is improving performance by up to 28% on execution times compared to a not adjusted POMDP.

This paper introduces a new sampling strategy and shows that superior performance can be obtained for a range of sampling based robotic motion planners, used in scenarios with low task variance, as found in many vision guided pick and place operations. The strategy uses kernel density estimation to identify regions with high probability of containing configurations being part of feasible solutions, and use the estimation to bias sampling. The kernel densities are initialized with a uniform distribution and are continuously updated, whenever paths are successfully planned and optimized. The system is thereby self-learning and improves performance over time. The sampler is tested on a variety of planners and against other sampling methods in two different scenarios containing robotic arms with 6 degrees of freedom and compared to a state-of-the-art optimization based planning algorithm. Tests show that the sampler learns fast and improves both time taken for solving problems and the quality of the resulting paths compared to other samplers.

Vibratory bowl feeders are still among the most commonly used production equipment for automated part feeding, where parts are correctly oriented for further manipulation by being conveyed through a set of orienting devices. Designing vibratory bowl feeders involves selecting and sequencing a number of these devices that either reorients or rejects the part until a desirable orientation is achieved. To aid the designer in this task, this work presents a configuration system where knowledge of the behaviour for each device is acquired through dynamic simulation, and used to solve the configuration task. To test the approach, the configuration system is used to find three device sequences for feeding three parts in specific orientations. The sequences are validated through simulation and real world experiments, showing good consistency.

Vibratory bowl feeders (VBF) are widely used in industry, but their design process is time consuming. This paper outlines an approach for the automatic design of such feeders, and utilizes rigid body simulation for evaluating design configurations. To ensure the applicability of the simulation, the paper makes an extensive evaluation in simulation and compares it to real world experiments. The experiments show similar overall characteristics, but also reveal differences which need to be considered when using simulation as a tool for design. Finally the paper illustrates the design process by optimizing the parameters of two devices used for the orienting of parts (often referred to as traps), and tests their configurations in the real world.

SUMMARY It has become a common practice to use simulation to generate large databases of good grasps for grasp planning in robotics research. However, the existence of a generic simulation context that enables the generation of high quality grasps that can be used in several different contexts such as bin-picking or picking objects from a table, has to our knowledge not yet been discussed in the literature. In this paper, we investigate how well the quality of grasps simulated in a commonly used “generic” context transfers to a specific context, both, in simulation and in the real world. We generate a large database of grasp hypotheses for several objects and grippers, which we then evaluate in different dynamic simulation contexts e.g., free floating (no gravity, no obstacles), standing on a table and lying on a table. We present a comparison on the intersection of the grasp outcome space across the different contexts and quantitatively show that to generate reliable grasp databases, it is important to use context specific simulation. We furthermore evaluate how well a state of the art grasp database transfers from two simulated contexts to a real world context of picking an object from a table and discuss how to evaluate transferability into non-deterministic real world contexts.

Robotic assembly tasks are in general difficult to program and require a high degree of precision. As the complexity of the task increases it becomes increasingly unlikely that tasks can always be executed without errors. Preventing errors beyond a certain point is economically infeasible, in particular for small-batch productions. As an alternative, we propose a system for automatically handling certain classes of errors instead of preventing them. Specifically, we show that many operations can be automatically reversed. Errors can be handled through automatic reverse execution of the control program to a safe point, from which forward execution can be resumed. This paper describes the principles behind automatic reversal of robotic assembly operations, and experimentally demonstrates the use of a domain-specific language that supports automatic error handling through reverse execution. Our contribution represents the first experimental demonstration of reversible computing principles applied to industrial robotics.

Programming industrial robots for small-sized batch production of assembly operations is challenging due to the difficulty of precisely specifying general yet robust assembly operations. We observe that as the complexity of assembly increases, so does the likelihood of errors. We propose that certain classes of errors during assembly operations can be addressed using reverse execution, allowing the robot to temporarily back out of an erroneous situation, after which the assembly operation can be automatically retried. Moreover, reversibility can be used to automatically derive a disassembly sequence from a given assembly sequence, or vice versa.This paper presents the initial design of the RASQ domain-specific language (DSL) for specifying such assembly sequences, based on initial experiments using an industrial case study. The language is defined in terms of a formal semantics corresponding to a realistic execution model currently under implementation. The DSL is used as part of a software framework that aims at tackling uncertainties through a combination of reverse and probabilistic execution.