Jim Torresen

Tom F. Hansen, Georg H. Erharter, Zhongqiang Liu et al.

Current rock engineering design in drill and blast tunnelling primarily relies on engineers' observational assessments. Measure While Drilling (MWD) data, a high-resolution sensor dataset collected during tunnel excavation, is underutilised, mainly serving for geological visualisation. This study aims to automate the translation of MWD data into actionable metrics for rock engineering. It seeks to link data to specific engineering actions, thus providing critical decision support for geological challenges ahead of the tunnel face. Leveraging a large and geologically diverse dataset of 500,000 drillholes from 15 tunnels, the research introduces models for accurate rock mass quality classification in a real-world tunnelling context. Both conventional machine learning and image-based deep learning are explored to classify MWD data into Q-classes and Q-values, examples of metrics describing the stability of the rock mass, using both tabular and image data. The results indicate that the K-nearest neighbours algorithm in an ensemble with tree-based models using tabular data, effectively classifies rock mass quality. It achieves a cross-validated balanced accuracy of 0.86 in classifying rock mass into the Q-classes A, B, C, D, E1, E2, and 0.95 for a binary classification with E versus the rest. Classification using a CNN with MWD-images for each blasting round resulted in a balanced accuracy of 0.82 for binary classification. Regressing the Q-value from tabular MWD-data achieved cross-validated R2 and MSE scores of 0.80 and 0.18 for a similar ensemble model as in classification. High performance in regression and classification boosts confidence in automated rock mass assessment. Applying advanced modelling on a unique dataset demonstrates MWD data's value in improving rock mass classification accuracy and advancing data-driven rock engineering design, reducing manual intervention.

Yumi Iwashita, Haakon Moe, Yang Cheng et al.

As global efforts to explore the Moon intensify, the need for high-quality 3D lunar maps becomes increasingly critical-particularly for long-distance missions such as NASA's Endurance mission concept, in which a rover aims to traverse 2,000 km across the South Pole-Aitken basin. Kaguya TC (Terrain Camera) images, though globally available at 10 m/pixel, suffer from altitude inaccuracies caused by stereo matching errors and JPEG-based compression artifacts. This paper presents a method to improve the quality of 3D maps generated from Kaguya TC images, focusing on mitigating the effects of compression-induced noise in disparity maps. We analyze the compression behavior of Kaguya TC imagery, and identify systematic disparity noise patterns, especially in darker regions. In this paper, we propose an approach to enhance 3D map quality by reducing residual noise in disparity images derived from compressed images. Our experimental results show that the proposed approach effectively reduces elevation noise, enhancing the safety and reliability of terrain data for future lunar missions.

Ulysse Côté-Allard, Minh H. Pham, Alexandra K. Schultz et al.

Internet-delivered psychological treatments (IDPT) are seen as an effective and scalable pathway to improving the accessibility of mental healthcare. Within this context, treatment adherence is an especially pertinent challenge to address due to the reduced interaction between healthcare professionals and patients. In parallel, the increase in regulations surrounding the use of personal data, such as the General Data Protection Regulation (GDPR), makes data minimization a core consideration for real-world implementation of IDPTs. Consequently, this work proposes a Self-Attention-based deep learning approach to perform automatic adherence forecasting, while only relying on minimally sensitive login/logout-timestamp data. This approach was tested on a dataset containing 342 patients undergoing Guided Internet-delivered Cognitive Behavioral Therapy (G-ICBT) treatment. Of these 342 patients, 101 (~30%) were considered non-adherent (dropout) based on the adherence definition used in this work (i.e. at least eight connections to the platform lasting more than a minute over 56 days). The proposed model achieved over 70% average balanced accuracy, after only 20 out of the 56 days (~1/3) of the treatment had elapsed. This study demonstrates that automatic adherence forecasting for G-ICBT, is achievable using only minimally sensitive data, thus facilitating the implementation of such tools within real-world IDPT platforms.

Ulysse Côté-Allard, Petter Jakobsen, Andrea Stautland et al.

Manic episodes of bipolar disorder can lead to uncritical behaviour and delusional psychosis, often with destructive consequences for those affected and their surroundings. Early detection and intervention of a manic episode are crucial to prevent escalation, hospital admission and premature death. However, people with bipolar disorder may not recognize that they are experiencing a manic episode and symptoms such as euphoria and increased productivity can also deter affected individuals from seeking help. This work proposes to perform user-independent, automatic mood-state detection based on actigraphy and electrodermal activity acquired from a wrist-worn device during mania and after recovery (euthymia). This paper proposes a new deep learning-based ensemble method leveraging long (20h) and short (5 minutes) time-intervals to discriminate between the mood-states. When tested on 47 bipolar patients, the proposed classification scheme achieves an average accuracy of 91.59% in euthymic/manic mood-state recognition.

Charles Patrick Martin, Alexander Refsum Jensenius, Jim Torresen

This paper describes the process of developing a standstill performance work using the Myo gesture control armband and the Bela embedded computing platform. The combination of Myo and Bela allows a portable and extensible version of the standstill performance concept while introducing muscle tension as an additional control parameter. We describe the technical details of our setup and introduce Myo-to-Bela and Myo-to-OSC software bridges that assist with prototyping compositions using the Myo controller.

Benedikte Wallace, Charles P. Martin, Jim Torresen et al.

Sound and movement are closely coupled, particularly in dance. Certain audio features have been found to affect the way we move to music. Is this relationship between sound and movement something which can be modelled using machine learning? This work presents initial experiments wherein high-level audio features calculated from a set of music pieces are included in a movement generation model trained on motion capture recordings of improvised dance. Our results indicate that the model learns to generate realistic dance movements which vary depending on the audio features.

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.

Trenton Schulz, Patrick Holthaus, Farshid Amirabdollahian et al.

We investigated how a robot moving with different velocity profiles affects a person's perception of it when working together on a task. The two profiles are the common linear profile and a profile based on the animation principles of slow in, slow out. The investigation was accomplished by running an experiment in a home context where people and the robot cooperated on a clean-up task. We used the Godspeed series of questionnaires to gather people's perception of the robot. Average scores for each series appear not to be different enough to reject the null hypotheses, but looking at the component items provides paths to future areas of research. We also discuss the scenario for the experiment and how it may be used for future research into using animation techniques for moving robots and improving the legibility of a robot's locomotion.

Charles P Martin, Jim Torresen

This paper is about creating digital musical instruments where a predictive neural network model is integrated into the interactive system. Rather than predicting symbolic music (e.g., MIDI notes), we suggest that predicting future control data from the user and precise temporal information can lead to new and interesting interactive possibilities. We propose that a mixture density recurrent neural network (MDRNN) is an appropriate model for this task. The predictions can be used to fill-in control data when the user stops performing, or as a kind of filter on the user's own input. We present an interactive MDRNN prediction server that allows rapid prototyping of new NIMEs featuring predictive musical interaction by recording datasets, training MDRNN models, and experimenting with interaction modes. We illustrate our system with several example NIMEs applying this idea. Our evaluation shows that real-time predictive interaction is viable even on single-board computers and that small models are appropriate for small datasets.

Kai Olav Ellefsen, Jim Torresen

A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the challenge of learning accurate models of an environment. If such a model is inaccurate, the agent's plans and actions will likely be sub-optimal, and likely lead to the wrong outcomes. Recent progress in model-based reinforcement learning has improved the ability for agents to learn and use predictive models. In this paper, we extend a recent deep learning architecture which learns a predictive model of the environment that aims to predict only the value of a few key measurements, which are be indicative of an agent's performance. Predicting only a few measurements rather than the entire future state of an environment makes it more feasible to learn a valuable predictive model. We extend this predictive model with a small, evolving neural network that suggests the best goals to pursue in the current state. We demonstrate that this allows the predictive model to transfer to new scenarios where goals are different, and that the adaptive goals can even adjust agent behavior on-line, changing its strategy to fit the current context.

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.

Kai Olav Ellefsen, Joost Huizinga, Jim Torresen

The structure and performance of neural networks are intimately connected, and by use of evolutionary algorithms, neural network structures optimally adapted to a given task can be explored. Guiding such neuroevolution with additional objectives related to network structure has been shown to improve performance in some cases, especially when modular neural networks are beneficial. However, apart from objectives aiming to make networks more modular, such structural objectives have not been widely explored. We propose two new structural objectives and test their ability to guide evolving neural networks on two problems which can benefit from decomposition into subtasks. The first structural objective guides evolution to align neural networks with a user-recommended decomposition pattern. Intuitively, this should be a powerful guiding target for problems where human users can easily identify a structure. The second structural objective guides evolution towards a population with a high diversity in decomposition patterns. This results in exploration of many different ways to decompose a problem, allowing evolution to find good decompositions faster. Tests on our target problems reveal that both methods perform well on a problem with a very clear and decomposable structure. However, on a problem where the optimal decomposition is less obvious, the structural diversity objective is found to outcompete other structural objectives -- and this technique can even increase performance on problems without any decomposable structure at all.

Charles P Martin, Jim Torresen

The widespread adoption of mobile devices, such as smartphones and tablets, has made touchscreens a common interface for musical performance. New mobile musical instruments have been designed that embrace collaborative creation and that explore the affordances of mobile devices, as well as their constraints. While these have been investigated from design and user experience perspectives, there is little examination of the performers' musical outputs. In this work, we introduce a constrained touchscreen performance app, MicroJam, designed to enable collaboration between performers, and engage in a novel data-driven analysis of more than 1600 performances using the app. MicroJam constrains performances to five seconds, and emphasises frequent and casual music making through a social media-inspired interface. Performers collaborate by replying to performances, adding new musical layers that are played back at the same time. Our analysis shows that users tend to focus on the centre and diagonals of the touchscreen area, and tend to swirl or swipe rather than tap. We also observe that while long swipes dominate the visual appearance of performances, the majority of interactions are short with limited expressive possibilities. Our findings are summarised into a set of design recommendations for MicroJam and other touchscreen apps for social musical interaction.

Kai Olav Ellefsen, Charles Patrick Martin, Jim Torresen

Gaining a better understanding of how and what machine learning systems learn is important to increase confidence in their decisions and catalyze further research. In this paper, we analyze the predictions made by a specific type of recurrent neural network, mixture density RNNs (MD-RNNs). These networks learn to model predictions as a combination of multiple Gaussian distributions, making them particularly interesting for problems where a sequence of inputs may lead to several distinct future possibilities. An example is learning internal models of an environment, where different events may or may not occur, but where the average over different events is not meaningful. By analyzing the predictions made by trained MD-RNNs, we find that their different Gaussian components have two complementary roles: 1) Separately modeling different stochastic events and 2) Separately modeling scenarios governed by different rules. These findings increase our understanding of what is learned by predictive MD-RNNs, and open up new research directions for further understanding how we can benefit from their self-organizing model decomposition.

Trenton Schulz, Jim Torresen, Jo Herstad

There are many different ways a robot can move in Human-Robot Interaction. One way is to use techniques from film animation to instruct the robot to move. This article is a systematic literature review of human-robot trials, pilots, and evaluations that have applied techniques from animation to move a robot. Through 27 articles, we find that animation techniques improves individual's interaction with robots, improving individual's perception of qualities of a robot, understanding what a robot intends to do, and showing the robot's state, or possible emotion. Animation techniques also help people relate to robots that do not resemble a human or robot. The studies in the articles show further areas for research, such as applying animation principles in other types of robots and situations, combining animation techniques with other modalities, and testing robots moving with animation techniques over the long term.

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.

Charles P. Martin, Kai Olav Ellefsen, Jim Torresen

Musical performance requires prediction to operate instruments, to perform in groups and to improvise. In this paper, we investigate how a number of digital musical instruments (DMIs), including two of our own, have applied predictive machine learning models that assist users by predicting unknown states of musical processes. We characterise these predictions as focussed within a musical instrument, at the level of individual performers, and between members of an ensemble. These models can connect to existing frameworks for DMI design and have parallels in the cognitive predictions of human musicians. We discuss how recent advances in deep learning highlight the role of prediction in DMIs, by allowing data-driven predictive models with a long memory of past states. The systems we review are used to motivate musical use-cases where prediction is a necessary component, and to highlight a number of challenges for DMI designers seeking to apply deep predictive models in interactive music systems of the future.

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.

Charles P. Martin, Jim Torresen

RoboJam is a machine-learning system for generating music that assists users of a touchscreen music app by performing responses to their short improvisations. This system uses a recurrent artificial neural network to generate sequences of touchscreen interactions and absolute timings, rather than high-level musical notes. To accomplish this, RoboJam's network uses a mixture density layer to predict appropriate touch interaction locations in space and time. In this paper, we describe the design and implementation of RoboJam's network and how it has been integrated into a touchscreen music app. A preliminary evaluation analyses the system in terms of training, musical generation and user interaction.

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.