The study of self-assembling robots represents a promising strand within the emerging field of modular robots research. Self-assembling robots have the potential to autonomously adapt their bodies to new tasks and changing environments long after their initial deployment by forming new or reorganizing existing physical connections to peer robots. In previous research, many approaches have been presented to enable self-assembling robots to form composite morphologies. Recent technological advances have also increased the number of robots able to form such morphologies by at least two orders of magnitude. However, to date, composite robot morphologies have not been able to solve real-world tasks nor have they been able to adapt to changing conditions entirely without human assistance or prior knowledge.In this thesis, we identify three reasons why self-assembling robots may not have been able to fully unleash their potential and propose appropriate solutions. First, composite morphologies are not able to show sensorimotor coordination similar to those seen in their monolithic counterparts. We propose "mergeable nervous systems" -- a novel methodology that unifies independent robotic units into a single holistic entity at the control level. Our experiments show that mergeable nervous systems can enable self-assembling robots to demonstrate feats that go beyond those seen in any engineered or biological system. Second, no proposal has been tabled to enable a robot in a decentralized multirobot system select its communication partners based on their location. We propose a new form of highly scalable mechanism to enable "spatially targeted communication" in such systems. Third, the question of when and how to trigger a self-assembly process has been ignored by researchers to a large extent. We propose "supervised morphogenesis" -- a control methodology that is based on spatially targeted communication and enables cooperation between aerial and ground-based self-assembling robots. We show that allocating self-assembly related decision-making to a robot with an aerial perspective of the environment can allow robots on the ground to operate in entirely unknown environments and to solve tasks that arise during mission time. For each of the three propositions put forward in this thesis, we present results of extensive experiments carried out on real robotic hardware. Our results confirm that we were able to substantially advance the state of the art in self-assembling robots by unleashing their potential for morphological adaptation through enhanced sensorimotor coordination and by improving their overall autonomy through cooperation with aerial robots. / Doctorat en Sciences de l'ingénieur et technologie / info:eu-repo/semantics/nonPublished

Successful applications of Reinforcement Learning (RL) in the robotics field has proliferated after DeepMind and OpenAI showed the ability of RL techniques to develop intelligent robotic systems that could learn to perform complex tasks. Ever since the use of robots for surgical procedures, researchers have been trying to bring some sort of autonomy into the operating room. Surgical robotic systems such as da Vinci currently provide the surgeons with direct control. To relieve the stress and the burden on the surgeon using the da Vinci robot, semi-automating or automating surgical tasks such as suturing can be beneficial. This work presents a RL-based approach to automate the needle hand-off task. It puts forward two approaches based on the type of environment, a discrete and continuous space approach. For capturing a unique suturing style, user data was collected using the da Vinci Research Kit to generate a sparse reward function. It was used to derive an optimal policy using Q-learning for a discretized environment. Further, a RL framework for da Vinci Research Kit was developed using a real-time dynamics simulator - Asynchronous Multi-Body Framework (AMBF). A model was trained and evaluated to reach the desired goal using model-free RL techniques while considering the dynamics of the robot to help mitigate the difficulty in transferring trained model to real-world robots. Therefore, the developed RL framework would enable the RL community to train surgical robots using state of the art RL techniques and transfer it to real-world robots with minimal effort. Based on the results obtained, the viability of applying RL techniques to develop a supervised level of autonomy for performing surgical tasks is discussed. To summarize, this work mainly focuses on using RL to automate the suture hand-off task in order to move a step towards solving the greater problem of automating suturing.

Advances in mobile robot technology allow an increasing variety of applications to be imagined, including: search and rescue, exploration of unknown areas and working with hazardous materials. State of the art robots are able to behave autonomously and without direct human control, using on-board devices to perceive, navigate and reason about the world. Unmanned Aerial Vehicles (UAVs) are particularly well suited to performing advanced sensing tasks by moving rapidly through the environment irrespective of the terrain. Deploying groups of mobile robots offers advantages, such as robustness to individual failures and a reduction in task completion time. However, to operate efficiently these teams require specific approaches to enable the individual agents to cooperate. This thesis proposes coordinated approaches to search scenarios for teams of UAVs. The primary application considered is Wilderness Search and Rescue (WiSaR), although the techniques developed are applicable elsewhere. A novel frontier-based search approach is developed for rotor-craft UAVs, taking advantage of available terrain information to minimise altitude changes during flight. This is accompanied by a lightweight coordination mechanism to enable cooperative behaviour with minimal additional overhead. The concept of a team rendezvous is introduced, at which all team members attend to exchange data. This also provides an ideal opportunity to create a comprehensive team solution to relay newly gathered data to a base station. Furthermore, the delay between sensing and the acquired data becoming available to mission commanders is analysed and a technique proposed for adapting the team to meet a latency requirement. These approaches are evaluated and characterised experimentally through simulation. Coordinated frontier search is shown to outperform greedy walk methods, reducing redundant sensing coverage using only a minimal coordination protocol. Combining the search, rendezvous and relay techniques provides a holistic approach to the deployment of UAV teams, meeting mission objectives without extensive pre-configuration.

Multi-vehicle systems offer many advantages in engineering applications such as increased efficiency and robustness. However, the disadvantage of multi-vehicle systems is that they require a high level of organization and coordination in order to successfully complete a task. Formation control is a field of engineering that addresses this issue, and provides coordination schemes to successfully implement multi-vehicle systems. Two approaches to group coordination were proposed in this work: geometric and self-organizing formations. A geometric reconfiguring formation was developed using the leader-follower method, and the self-organizing formation was developed using the velocity potential equations from fluid flow theory. Both formation controllers were first tested in simulation in MATLAB, and then implemented on the X80 mobile robot units. Various experiments were conducted to test the formations under difficult obstacle scenarios. The robots successfully navigated through the obstacles as a coordinated as a team using the self-organizing and geometric formation control approaches.

Multi-vehicle systems offer many advantages in engineering applications such as increased efficiency and robustness. However, the disadvantage of multi-vehicle systems is that they require a high level of organization and coordination in order to successfully complete a task. Formation control is a field of engineering that addresses this issue, and provides coordination schemes to successfully implement multi-vehicle systems. Two approaches to group coordination were proposed in this work: geometric and self-organizing formations. A geometric reconfiguring formation was developed using the leader-follower method, and the self-organizing formation was developed using the velocity potential equations from fluid flow theory. Both formation controllers were first tested in simulation in MATLAB, and then implemented on the X80 mobile robot units. Various experiments were conducted to test the formations under difficult obstacle scenarios. The robots successfully navigated through the obstacles as a coordinated as a team using the self-organizing and geometric formation control approaches.

Human-controlled robots are utilized in many situations and such use is becoming widespread. This thesis details research that allows a single human to interact with a team of robots performing tasks that require cooperation. The research provides insight into effective interaction design methods and appropriate interface techniques. The use of team-level autonomy is shown to decrease human workload while simultaneously improving individual robot efficiency and robot-team cooperation. An indoor human-robot interaction testbed was developed at the BYU MAGICC Lab to facilitate experimentation. The testbed consists of eight robots equipped with wireless modems, a field on which the robots move, an overhead camera and image processing software which tracks robot position and heading, a simulator which allows development and testing without hardware utilization and a graphical user interface which enables human control of either simulated or hardware robots. The image processing system was essential for effective robot hardware operation and is described in detail. The system produced accurate robot position and heading information 30 times per second for a maximum of 12 robots, was relatively insensitive to lighting conditions and was easily reconfigurable. The completed testbed was utilized to create a game for testing human-robot interaction schemes. The game required a human controlling three robots to find and tag three robot opponents in a maze. Finding an opponent could be accomplished by individual robots, but tagging an opponent required cooperation between at least two robots. The game was played by 11 subjects in five different autonomy modes ranging from limited robot autonomy to advanced individual autonomy with basic team-level autonomy. Participants were interrupted during the game by a secondary spatial reasoning task which prevented them from interacting with the robots for short periods of time. Robot performance during that interruption provided a measure of both individual and team neglect tolerance. Individual robot neglect tolerance and performance did not directly correspond to those quantities at the team level. The interaction mode with the highest levels of individual and team autonomy was most effective; it minimized game time and human workload and maximized team neglect tolerance.

<p>Human multi-robot systems constitute a relatively new area of research that focuses on the interaction and collaboration between humans and multiple robots. Well-designed systems can enable a team of humans and robots to effectively work together on complex and sophisticated tasks such as exploration, monitoring, and search and rescue operations. This dissertation introduces an affective workload allocation system capable of adaptively allocating workload in real-time while considering the conditions and work performance of human operators in multi-human multi-robot teams. The proposed system is largely composed of three parts, taking the surveillance scenario involving multi-human operators and multi-robot system as an example. The first part of the system is a framework for an adaptive multi-human multi-robot system that allows real-time measurement and communication between heterogeneous sensors and multi-robot systems. The second part is an algorithm for real-time monitoring of humans' affective states using machine learning techniques and estimation of the affective state from multimodal data that consists of physiological and behavioral signals. The third part is a deep reinforcement learning-based workload allocation algorithm. For the first part of the affective workload allocation system, we developed a robot operating system (ROS)-based affective monitoring framework to enable communication among multiple wearable biosensors, behavioral monitoring devices, and multi-robot systems using the real-time operating system feature of ROS. We validated the sub-interfaces of the affective monitoring framework through connecting to a robot simulation and utilizing the framework to create a dataset. The dataset included various visual and physiological data categorized on the cognitive load level. The targeted cognitive load is stimulated by a closed-circuit television (CCTV) monitoring task on the surveillance scenario with multi-robot systems. Furthermore, we developed a deep learning-based affective prediction algorithm using the physiological and behavioral data captured from wearable biosensors and behavior-monitoring devices, in order to estimate the cognitive states for the second part of the system. For the third part of the affective workload allocation system, we developed a deep reinforcement learning-based workload allocation algorithm to allocate optimal workloads based on a human operator's performance. The algorithm was designed to take an operator's cognitive load, using objective and subjective measurements as inputs, and consider the operator's task performance model we developed using the empirical findings of the extensive user experiments, to allocate optimal workloads to human operators. We validated the proposed system through within-subjects study experiments on a generalized surveillance scenario involving multiple humans and multiple robots in a team. The multi-human multi-robot surveillance environment included an affective monitoring framework and an affective prediction algorithm to read sensor data and predict human cognitive load in real-time, respectively. We investigated optimal methods for affective workload allocations by comparing other allocation strategies used in the user experiments. As a result, we demonstrated the effectiveness and performance of the proposed system. Moreover, we found that the subjective and objective measurement of an operator's cognitive loads and the process of seeking consent for the workload transitions must be included in the workload allocation system to improve the team performance of the multi-human multi-robot teams.</p>