Kyrre Glette

Birk Torpmann-Hagen, Vajira Thambawita, Kyrre Glette et al.

Generalizability is seen as one of the major challenges in deep learning, in particular in the domain of medical imaging, where a change of hospital or in imaging routines can lead to a complete failure of a model. To tackle this, we introduce Consistency Training, a training procedure and alternative to data augmentation based on maximizing models' prediction consistency across augmented and unaugmented data in order to facilitate better out-of-distribution generalization. To this end, we develop a novel region-based segmentation loss function called Segmentation Inconsistency Loss (SIL), which considers the differences between pairs of augmented and unaugmented predictions and labels. We demonstrate that Consistency Training outperforms conventional data augmentation on several out-of-distribution datasets on polyp segmentation, a popular medical task.

K. Ege de Bruin, Kyrre Glette, Kai Olav Ellefsen et al.

Optimizing the body and brain of a robot is a coupled challenge: the morphology determines what control strategies are effective, while the control parameters influence how well the morphology performs. This joint optimization can be done through nested loops of evolutionary and learning processes, where the control parameters of each robot are learned independently. However, the control parameters learned by one robot may contain valuable information for others. Thus, we introduce a social learning approach in which robots can exploit optimized parameters from their peers to accelerate their own brain optimization. Within this framework, we systematically investigate how the selection of teachers, deciding which and how many robots to learn from, affects performance, experimenting with virtual soft robots in four tasks and environments. In particular, we study the effect of inheriting experience from morphologically similar robots due to the tightly coupled body and brain in robot optimization. Our results confirm the effectiveness of building on others' experience, as social learning clearly outperforms learning from scratch under equivalent computational budgets. In addition, while the optimal teacher selection strategy remains open, our findings suggest that incorporating knowledge from multiple teachers can yield more consistent and robust improvements.

Etor Arza, Frank Veenstra, Tønnes F. Nygaard et al.

The design (shape) of a robot is usually decided before the control is implemented. This might limit how well the design is adapted to a task, as the suitability of the design is given by how well the robot performs in the task, which requires both a design and a controller. The co-optimization or simultaneous optimization of the design and control of robots addresses this limitation by producing a design and control that are both adapted to the task. This paper investigates some of the challenges inherent in the co-optimization of design and control in simulation. The results show that reducing how well the controllers are trained during the co-optimization process significantly improves the robot's performance when considering a second phase in which the controller for the best design is retrained with additional resources. In addition, the results demonstrate that the computation budget allocated to training the controller for each design influences design complexity, with simpler designs associated with lower training budgets. This paper experimentally studies key questions discussed in other works in the literature on the co-optimization of design and control of robots in simulation in four different co-optimization problems.

K. Ege de Bruin, Kyrre Glette, Kai Olav Ellefsen

The co-optimization of a robot's body and brain presents a coupled challenge: the morphology constrains which control strategies are effective, while the control determines how well the morphology performs. To address this, we combine morphology optimization as evolution with controller optimization as lifetime learning, utilizing Lamarckian inheritance to transfer learned controller parameters from parent to offspring. In dynamic environments, existing literature presents conflicting evidence: while traditional evolutionary theory often suggests Lamarckian inheritance lacks benefit, recent studies in evolutionary robotics indicate it can improve performance. We hypothesize that this is because previous works have not included all relevant variables with dynamic environments. In this work, we show that the benefit of Lamarckian inheritance depends on two variables: how conflicting the environmental changes are to robot control, and the predictability of those changes for the robotic agent. Using virtual soft robots and two different learning approaches, Bayesian optimization and reinforcement learning, we show that Lamarckian inheritance only underperforms Darwinian inheritance when the changes are both conflicting and unpredictable. We find that adding a sensor to detect environmental changes restores the benefits for Lamarckian inheritance in conflicting environments, by allowing robotic agents to predict the need for a different behavior, thereby generalizing their control.

Jinyue Guo, Anna-Maria Christodoulou, Balint Laczko et al.

Evolutionary Algorithms and Generative Deep Learning have been two of the most powerful tools for sound generation tasks. However, they have limitations: Evolutionary Algorithms require complicated designs, posing challenges in control and achieving realistic sound generation. Generative Deep Learning models often copy from the dataset and lack creativity. In this paper, we propose LVNS-RAVE, a method to combine Evolutionary Algorithms and Generative Deep Learning to produce realistic and novel sounds. We use the RAVE model as the sound generator and the VGGish model as a novelty evaluator in the Latent Vector Novelty Search (LVNS) algorithm. The reported experiments show that the method can successfully generate diversified, novel audio samples under different mutation setups using different pre-trained RAVE models. The characteristics of the generation process can be easily controlled with the mutation parameters. The proposed algorithm can be a creative tool for sound artists and musicians.

Ege de Bruin, Kyrre Glette, Kai Olav Ellefsen

It is well known that intra-life learning, defined as an additional controller optimization loop, is beneficial for evolving robot morphologies for locomotion. In this work, we investigate this further by comparing it in two different environments: an easy flat environment and a more challenging hills environment. We show that learning is significantly more beneficial in a hilly environment than in a flat environment and that it might be needed to evaluate robots in a more challenging environment to see the benefits of learning.

Emma Hjellbrekke Stensby, Kai Olav Ellefsen, Kyrre Glette

Designing robots by hand can be costly and time consuming, especially if the robots have to be created with novel materials, or be robust to internal or external changes. In order to create robots automatically, without the need for human intervention, it is necessary to optimise both the behaviour and the body design of the robot. However, when co-optimising the morphology and controller of a locomoting agent the morphology tends to converge prematurely, reaching a local optimum. Approaches such as explicit protection of morphological innovation have been used to reduce this problem, but it might also be possible to increase exploration of morphologies using a more indirect approach. We explore how changing the environment, where the agent locomotes, affects the convergence of morphologies. The agents' morphologies and controllers are co-optimised, while the environments the agents locomote in are evolved open-endedly with the Paired Open-Ended Trailblazer (POET). We compare the diversity, fitness and robustness of agents evolving in environments generated by POET to agents evolved in handcrafted curricula of environments. Our agents each contain of a population of individuals being evolved with a genetic algorithm. This population is called the agent-population. We show that agent-populations evolving in open-endedly evolving environments exhibit larger morphological diversity than agent-populations evolving in hand crafted curricula of environments. POET proved capable of creating a curriculum of environments which encouraged both diversity and quality in the populations. This suggests that POET may be capable of reducing premature convergence in co-optimisation of morphology and controllers.

Jørgen Nordmoen, Frank Veenstra, Kai Olav Ellefsen et al.

In modular robotics, modules can be reconfigured to change the morphology of the robot, making it able to adapt for specific tasks. However, optimizing both the body and control is a difficult challenge due to the intricate relationship between fine-tuning control and morphological changes that can invalidate such optimizations. To solve this challenge we compare three different Evolutionary Algorithms on their capacity to optimize morphologies in modular robotics. We compare two objective-based search algorithms, with MAP-Elites. To understand the benefit of diversity we transition the evolved populations into two difficult environments to see if diversity can have an impact on solving complex environments. In addition, we analyse the genealogical ancestry to shed light on the notion of stepping stones as key to enable high performance. The results show that MAP-Elites is capable of evolving the highest performing solutions in addition to generating the largest morphological diversity. For the transition between environments the results show that MAP-Elites is better at regaining performance by promoting morphological diversity. With the analysis of genealogical ancestry we show that MAP-Elites produces more diverse and higher performing stepping stones than the other objective-based search algorithms. Transitioning the populations to more difficult environments show the utility of morphological diversity, while the analysis of stepping stones show a strong correlation between diversity of ancestry and maximum performance on the locomotion task. The paper shows the advantage of promoting diversity for solving a locomotion task in different environments for modular robotics. By showing that the quality and diversity of stepping stones in Evolutionary Algorithms is an important factor for overall performance we have opened up a new area of analysis and results.

Jørgen Nordmoen, Frank Veenstra, Kai Olav Ellefsen et al.

In Evolutionary Robotics a population of solutions is evolved to optimize robots that solve a given task. However, in traditional Evolutionary Algorithms, the population of solutions tends to converge to local optima when the problem is complex or the search space is large, a problem known as premature convergence. Quality Diversity algorithms try to overcome premature convergence by introducing additional measures that reward solutions for being different while not necessarily performing better. In this paper we compare a single objective Evolutionary Algorithm with two diversity promoting search algorithms; a Multi-Objective Evolutionary Algorithm and MAP-Elites a Quality Diversity algorithm, for the difficult problem of evolving control and morphology in modular robotics. We compare their ability to produce high performing solutions, in addition to analyze the evolved morphological diversity. The results show that all three search algorithms are capable of evolving high performing individuals. However, the Quality Diversity algorithm is better adept at filling all niches with high-performing solutions. This confirms that Quality Diversity algorithms are well suited for evolving modular robots and can be an important means of generating repertoires of high performing solutions that can be exploited both at design- and runtime.

Sondre A. Engebraaten, Jonas Moen, Oleg A. Yakimenko et al.

Multi-function swarms are swarms that solve multiple tasks at once. For example, a quadcopter swarm could be tasked with exploring an area of interest while simultaneously functioning as ad-hoc relays. With this type of multi-function comes the challenge of handling potentially conflicting requirements simultaneously. Using the Quality-Diversity algorithm MAP-elites in combination with a suitable controller structure, a framework for automatic behavior generation in multi-function swarms is proposed. The framework is tested on a scenario with three simultaneous tasks: exploration, communication network creation and geolocation of RF emitters. A repertoire is evolved, consisting of a wide range of controllers, or behavior primitives, with different characteristics and trade-offs in the different tasks. This repertoire would enable the swarm to transition between behavior trade-offs online, according to the situational requirements. Furthermore, the effect of noise on the behavior characteristics in MAP-elites is investigated. A moderate number of re-evaluations is found to increase the robustness while keeping the computational requirements relatively low. A few selected controllers are examined, and the dynamics of transitioning between these controllers are explored. Finally, the study develops a methodology for analyzing the makeup of the resulting controllers. This is done through a parameter variation study where the importance of individual inputs to the swarm controllers is assessed and analyzed.

Jørgen Nordmoen, Tønnes Frostad Nygaard, Eivind Samuelsen et al.

Real-valued genotypes together with the variation operators, mutation and crossover, constitute some of the fundamental building blocks of Evolutionary Algorithms. Real-valued genotypes are utilized in a broad range of contexts, from weights in Artificial Neural Networks to parameters in robot control systems. Shared between most uses of real-valued genomes is the need for limiting the range of individual parameters to allowable bounds. In this paper we will illustrate the challenge of limiting the parameters of real-valued genomes and analyse the most promising method to properly limit these values. We utilize both empirical as well as benchmark examples to demonstrate the utility of the proposed method and through a literature review show how the insight of this paper could impact other research within the field. The proposed method requires minimal intervention from Evolutionary Algorithm practitioners and behaves well under repeated application of variation operators, leading to better theoretical properties as well as significant differences in well-known benchmarks.

Tonnes F. Nygaard, David Howard, Kyrre Glette

Evolutionary algorithms offer great promise for the automatic design of robot bodies, tailoring them to specific environments or tasks. Most research is done on simplified models or virtual robots in physics simulators, which do not capture the natural noise and richness of the real world. Very few of these virtual robots are built as physical robots, and the few that are will rarely be further improved in the actual environment they operate in, limiting the effectiveness of the automatic design process. We utilize our shape-shifting quadruped robot, which allows us to optimize the design in its real-world environment. The robot is able to change the length of its legs during operation, and is robust enough for complex experiments and tasks. We have co-evolved control and morphology in several different scenarios, and have seen that the algorithm is able to exploit the dynamic morphology solely through real-world experiments.

Tønnes F. Nygaard, Charles P. Martin, David Howard et al.

Robots operating in the real world will experience a range of different environments and tasks. It is essential for the robot to have the ability to adapt to its surroundings to work efficiently in changing conditions. Evolutionary robotics aims to solve this by optimizing both the control and body (morphology) of a robot, allowing adaptation to internal, as well as external factors. Most work in this field has been done in physics simulators, which are relatively simple and not able to replicate the richness of interactions found in the real world. Solutions that rely on the complex interplay between control, body, and environment are therefore rarely found. In this paper, we rely solely on real-world evaluations and apply evolutionary search to yield combinations of morphology and control for our mechanically self-reconfiguring quadruped robot. We evolve solutions on two distinct physical surfaces and analyze the results in terms of both control and morphology. We then transition to two previously unseen surfaces to demonstrate the generality of our method. We find that the evolutionary search finds high-performing and diverse morphology-controller configurations by adapting both control and body to the different properties of the physical environments. We additionally find that morphology and control vary with statistical significance between the environments. Moreover, we observe that our method allows for morphology and control parameters to transfer to previously-unseen terrains, demonstrating the generality of our approach.

Ulysse Côté-Allard, Gabriel Gagnon-Turcotte, Angkoon Phinyomark et al.

Surface electromyography (sEMG) provides an intuitive and non-invasive interface from which to control machines. However, preserving the myoelectric control system's performance over multiple days is challenging, due to the transient nature of the signals obtained with this recording technique. In practice, if the system is to remain usable, a time-consuming and periodic recalibration is necessary. In the case where the sEMG interface is employed every few days, the user might need to do this recalibration before every use. Thus, severely limiting the practicality of such a control method. Consequently, this paper proposes tackling the especially challenging task of unsupervised adaptation of sEMG signals, when multiple days have elapsed between each recording, by introducing Self-Calibrating Asynchronous Domain Adversarial Neural Network (SCADANN). SCADANN is compared with two state-of-the-art self-calibrating algorithms developed specifically for deep learning within the context of EMG-based gesture recognition and three state-of-the-art domain adversarial algorithms. The comparison is made both on an offline and a dynamic dataset (20 participants per dataset), using two different deep network architectures with two different input modalities (temporal-spatial descriptors and spectrograms). Overall, SCADANN is shown to substantially and systematically improves classification performances over no recalibration and obtains the highest average accuracy for all tested cases across all methods.

Ulysse Côté-Allard, Gabriel Gagnon-Turcotte, Angkoon Phinyomark et al.

Within the field of electromyography-based (EMG) gesture recognition, disparities exist between the offline accuracy reported in the literature and the real-time usability of a classifier. This gap mainly stems from two factors: 1) The absence of a controller, making the data collected dissimilar to actual control. 2) The difficulty of including the four main dynamic factors (gesture intensity, limb position, electrode shift, and transient changes in the signal), as including their permutations drastically increases the amount of data to be recorded. Contrarily, online datasets are limited to the exact EMG-based controller used to record them, necessitating the recording of a new dataset for each control method or variant to be tested. Consequently, this paper proposes a new type of dataset to serve as an intermediate between offline and online datasets, by recording the data using a real-time experimental protocol. The protocol, performed in virtual reality, includes the four main dynamic factors and uses an EMG-independent controller to guide movements. This EMG-independent feedback ensures that the user is in-the-loop during recording, while enabling the resulting dynamic dataset to be used as an EMG-based benchmark. The dataset is comprised of 20 able-bodied participants completing three to four sessions over a period of 14 to 21 days. The ability of the dynamic dataset to serve as a benchmark is leveraged to evaluate the impact of different recalibration techniques for long-term (across-day) gesture recognition, including a novel algorithm, named TADANN. TADANN consistently and significantly (p<0.05) outperforms using fine-tuning as the recalibration technique.

Tønnes F. Nygaard, Jørgen Nordmoen, Charles P. Martin et al.

Robots are used in more and more complex environments, and are expected to be able to adapt to changes and unknown situations. The easiest and quickest way to adapt is to change the control system of the robot, but for increasingly complex environments one should also change the body of the robot -- its morphology -- to better fit the task at hand. The theory of Embodied Cognition states that control is not the only source of cognition, and the body, environment, interaction between these and the mind all contribute as cognitive resources. Taking advantage of these concepts could lead to improved adaptivity, robustness, and versatility, however, executing these concepts on real-world robots puts additional requirements on the hardware and has several challenges when compared to learning just control. In contrast to the majority of work in Evolutionary Robotics, Eiben argues for real-world experiments in his `Grand Challenges for Evolutionary Robotics'. This requires robust hardware platforms that are capable of repeated experiments which should at the same time be flexible when unforeseen demands arise. In this paper, we introduce our unique robot platform with self-adaptive morphology. We discuss the challenges we have faced when designing it, and the lessons learned from real-world testing and learning.

Jørgen Nordmoen, Tønnes F. Nygaard, Kai Olav Ellefsen et al.

Overcoming robotics challenges in the real world requires resilient control systems capable of handling a multitude of environments and unforeseen events. Evolutionary optimization using simulations is a promising way to automatically design such control systems, however, if the disparity between simulation and the real world becomes too large, the optimization process may result in dysfunctional real-world behaviors. In this paper, we address this challenge by considering embodied phase coordination in the evolutionary optimization of a quadruped robot controller based on central pattern generators. With this method, leg phases, and indirectly also inter-leg coordination, are influenced by sensor feedback.By comparing two very similar control systems we gain insight into how the sensory feedback approach affects the evolved parameters of the control system, and how the performances differs in simulation, in transferal to the real world, and to different real-world environments. We show that evolution enables the design of a control system with embodied phase coordination which is more complex than previously seen approaches, and that this system is capable of controlling a real-world multi-jointed quadruped robot.The approach reduces the performance discrepancy between simulation and the real world, and displays robustness towards new environments.

Justinas Miseikis, Inka Brijacak, Saeed Yahyanejad et al.

Collaborative robots are becoming more common on factory floors as well as regular environments, however, their safety still is not a fully solved issue. Collision detection does not always perform as expected and collision avoidance is still an active research area. Collision avoidance works well for fixed robot-camera setups, however, if they are shifted around, Eye-to-Hand calibration becomes invalid making it difficult to accurately run many of the existing collision avoidance algorithms. We approach the problem by presenting a stand-alone system capable of detecting the robot and estimating its position, including individual joints, by using a simple 2D colour image as an input, where no Eye-to-Hand calibration is needed. As an extension of previous work, a two-stage transfer learning approach is used to re-train a multi-objective convolutional neural network (CNN) to allow it to be used with heterogeneous robot arms. Our method is capable of detecting the robot in real-time and new robot types can be added by having significantly smaller training datasets compared to the requirements of a fully trained network. We present data collection approach, the structure of the multi-objective CNN, the two-stage transfer learning training and test results by using real robots from Universal Robots, Kuka, and Franka Emika. Eventually, we analyse possible application areas of our method together with the possible improvements.

Tønnes Frostad Nygaard, Charles Patrick Martin, Jim Torresen et al.

The complexity of a legged robot's environment or task can inform how specialised its gait must be to ensure success. Evolving specialised robotic gaits demands many evaluations - acceptable for computer simulations, but not for physical robots. For some tasks, a more general gait, with lower optimization costs, could be satisfactory. In this paper, we introduce a new type of gait controller where complexity can be set by a single parameter, using a dynamic genotype-phenotype mapping. Low controller complexity leads to conservative gaits, while higher complexity allows more sophistication and high performance for demanding tasks, at the cost of optimization effort. We investigate the new controller on a virtual robot in simulations and do preliminary testing on a real-world robot. We show that having variable complexity allows us to adapt to different optimization budgets. With a high evaluation budget in simulation, a complex controller performs best. Moreover, real-world evolution with a limited evaluation budget indicates that a lower gait complexity is preferable for a relatively simple environment.

Justinas Miseikis, Inka Brijacak, Saeed Yahyanejad et al.

A significant problem of using deep learning techniques is the limited amount of data available for training. There are some datasets available for the popular problems like item recognition and classification or self-driving cars, however, it is very limited for the industrial robotics field. In previous work, we have trained a multi-objective Convolutional Neural Network (CNN) to identify the robot body in the image and estimate 3D positions of the joints by using just a 2D image, but it was limited to a range of robots produced by Universal Robots (UR). In this work, we extend our method to work with a new robot arm - Kuka LBR iiwa, which has a significantly different appearance and an additional joint. However, instead of collecting large datasets once again, we collect a number of smaller datasets containing a few hundred frames each and use transfer learning techniques on the CNN trained on UR robots to adapt it to a new robot having different shapes and visual features. We have proven that transfer learning is not only applicable in this field, but it requires smaller well-prepared training datasets, trains significantly faster and reaches similar accuracy compared to the original method, even improving it on some aspects.

Tønnes F. Nygaard, Charles P. Martin, Eivind Samuelsen et al.

For robots to handle the numerous factors that can affect them in the real world, they must adapt to changes and unexpected events. Evolutionary robotics tries to solve some of these issues by automatically optimizing a robot for a specific environment. Most of the research in this field, however, uses simplified representations of the robotic system in software simulations. The large gap between performance in simulation and the real world makes it challenging to transfer the resulting robots to the real world. In this paper, we apply real world multi-objective evolutionary optimization to optimize both control and morphology of a four-legged mammal-inspired robot. We change the supply voltage of the system, reducing the available torque and speed of all joints, and study how this affects both the fitness, as well as the morphology and control of the solutions. In addition to demonstrating that this real-world evolutionary scheme for morphology and control is indeed feasible with relatively few evaluations, we show that evolution under the different hardware limitations results in comparable performance for low and moderate speeds, and that the search achieves this by adapting both the control and the morphology of the robot.

Tønnes F. Nygaard, Charles P. Martin, Jim Torresen et al.

Evolutionary robotics has aimed to optimize robot control and morphology to produce better and more robust robots. Most previous research only addresses optimization of control, and does this only in simulation. We have developed a four-legged mammal-inspired robot that features a self-reconfiguring morphology. In this paper, we discuss the possibilities opened up by being able to efficiently do experiments on a changing morphology in the real world. We discuss present challenges for such a platform and potential experimental designs that could unlock new discoveries. Finally, we place our robot in its context within general developments in the field of evolutionary robotics, and consider what advances the future might hold.

Justinas Miseikis, Inka Brijacak, Saeed Yahyanejad et al.

The field of collaborative robotics and human-robot interaction often focuses on the prediction of human behaviour, while assuming the information about the robot setup and configuration being known. This is often the case with fixed setups, which have all the sensors fixed and calibrated in relation to the rest of the system. However, it becomes a limiting factor when the system needs to be reconfigured or moved. We present a deep learning approach, which aims to solve this issue. Our method learns to identify and precisely localise the robot in 2D camera images, so having a fixed setup is no longer a requirement and a camera can be moved. In addition, our approach identifies the robot type and estimates the 3D position of the robot base in the camera image as well as 3D positions of each of the robot joints. Learning is done by using a multi-objective convolutional neural network with four previously mentioned objectives simultaneously using a combined loss function. The multi-objective approach makes the system more flexible and efficient by reusing some of the same features and diversifying for each objective in lower layers. A fully trained system shows promising results in providing an accurate mask of where the robot is located and an estimate of its base and joint positions in 3D. We compare the results to our previous approach of using cascaded convolutional neural networks.

Tønnes F. Nygaard, Charles P. Martin, Jim Torresen et al.

If robots are to become ubiquitous, they will need to be able to adapt to complex and dynamic environments. Robots that can adapt their bodies while deployed might be flexible and robust enough to meet this challenge. Previous work on dynamic robot morphology has focused on simulation, combining simple modules, or switching between locomotion modes. Here, we present an alternative approach: a self-reconfigurable morphology that allows a single four-legged robot to actively adapt the length of its legs to different environments. We report the design of our robot, as well as the results of a study that verifies the performance impact of self-reconfiguration. This study compares three different control and morphology pairs under different levels of servo supply voltage in the lab. We also performed preliminary tests in different uncontrolled outdoor environments to see if changes to the external environment supports our findings in the lab. Our results show better performance with an adaptable body, lending evidence to the value of self-reconfiguration for quadruped robots.

Eivind Samuelsen, Kyrre Glette

In certain complex optimization tasks, it becomes necessary to use multiple measures to characterize the performance of different algorithms. This paper presents a method that combines ordinal effect sizes with Pareto dominance to analyze such cases. Since the method is ordinal, it can also generalize across different optimization tasks even when the performance measurements are differently scaled. Through a case study, we show that this method can discover and quantify relations that would be difficult to deduce using a conventional measure-by-measure analysis. This case study applies the method to the evolution of robot controller repertoires using the MAP-Elites algorithm. Here, we analyze the search performance across a large set of parametrizations; varying mutation size and operator type, as well as map resolution, across four different robot morphologies. We show that the average magnitude of mutations has a bigger effect on outcomes than their precise distributions.

Ulysse Côté-Allard, Cheikh Latyr Fall, Alexandre Drouin et al.

In recent years, deep learning algorithms have become increasingly more prominent for their unparalleled ability to automatically learn discriminant features from large amounts of data. However, within the field of electromyography-based gesture recognition, deep learning algorithms are seldom employed as they require an unreasonable amount of effort from a single person, to generate tens of thousands of examples. This work's hypothesis is that general, informative features can be learned from the large amounts of data generated by aggregating the signals of multiple users, thus reducing the recording burden while enhancing gesture recognition. Consequently, this paper proposes applying transfer learning on aggregated data from multiple users, while leveraging the capacity of deep learning algorithms to learn discriminant features from large datasets. Two datasets comprised of 19 and 17 able-bodied participants respectively (the first one is employed for pre-training) were recorded for this work, using the Myo Armband. A third Myo Armband dataset was taken from the NinaPro database and is comprised of 10 able-bodied participants. Three different deep learning networks employing three different modalities as input (raw EMG, Spectrograms and Continuous Wavelet Transform (CWT)) are tested on the second and third dataset. The proposed transfer learning scheme is shown to systematically and significantly enhance the performance for all three networks on the two datasets, achieving an offline accuracy of 98.31% for 7 gestures over 17 participants for the CWT-based ConvNet and 68.98% for 18 gestures over 10 participants for the raw EMG-based ConvNet. Finally, a use-case study employing eight able-bodied participants suggests that real-time feedback allows users to adapt their muscle activation strategy which reduces the degradation in accuracy normally experienced over time.

Justinas Miseikis, Patrick Knobelreiter, Inka Brijacak et al.

Many works in collaborative robotics and human-robot interaction focuses on identifying and predicting human behaviour while considering the information about the robot itself as given. This can be the case when sensors and the robot are calibrated in relation to each other and often the reconfiguration of the system is not possible, or extra manual work is required. We present a deep learning based approach to remove the constraint of having the need for the robot and the vision sensor to be fixed and calibrated in relation to each other. The system learns the visual cues of the robot body and is able to localise it, as well as estimate the position of robot joints in 3D space by just using a 2D color image. The method uses a cascaded convolutional neural network, and we present the structure of the network, describe our own collected dataset, explain the network training and achieved results. A fully trained system shows promising results in providing an accurate mask of where the robot is located and a good estimate of its joints positions in 3D. The accuracy is not good enough for visual servoing applications yet, however, it can be sufficient for general safety and some collaborative tasks not requiring very high precision. The main benefit of our method is the possibility of the vision sensor to move freely. This allows it to be mounted on moving objects, for example, a body of the person or a mobile robot working in the same environment as the robots are operating in.

Justinas Miseikis, Kyrre Glette, Ole Jakob Elle et al.

With advancing technologies, robotic manipulators and visual environment sensors are becoming cheaper and more widespread. However, robot control can be still a limiting factor for better adaptation of these technologies. Robotic manipulators are performing very well in structured workspaces, but do not adapt well to unexpected changes, like people entering the workspace. We present a method combining 3D Camera based workspace mapping, and a predictive and reflexive robot manipulator trajectory estimation to allow more efficient and safer operation in dynamic workspaces. In experiments on a real UR5 robot our method has proven to provide shorter and smoother trajectories compared to a reactive trajectory planner in the same conditions. Furthermore, the robot has successfully avoided any contact by initialising the reflexive movement even when an obstacle got unexpectedly close to the robot. The main goal of our work is to make the operation more flexible in unstructured dynamic workspaces and not just avoid obstacles, but also adapt when performing collaborative tasks with humans in the near future.

Justinas Miseikis, Kyrre Glette, Ole Jakob Elle et al.

With 3D sensing becoming cheaper, environment-aware and visually-guided robot arms capable of safely working in collaboration with humans will become common. However, a reliable calibration is needed, both for camera internal calibration, as well as Eye-to-Hand calibration, to make sure the whole system functions correctly. We present a framework, using a novel combination of well proven methods, allowing a quick automatic calibration for the integration of systems consisting of the robot and a varying number of 3D cameras by using a standard checkerboard calibration grid. Our approach allows a quick camera-to-robot recalibration after any changes to the setup, for example when cameras or robot have been repositioned. Modular design of the system ensures flexibility regarding a number of sensors used as well as different hardware choices. The framework has been proven to work by practical experiments to analyze the quality of the calibration versus the number of positions of the checkerboard used for each of the calibration procedures.