Improving Autonomous Robotic Navigation Using Imitation Learning.
Ontology highlight
ABSTRACT:
SUBMITTER: Cesar-Tondreau B
PROVIDER: S-EPMC8204187 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:While all minimally invasive procedures involve navigating from a small incision in the skin to the site of the intervention, it has not been previously demonstrated how this can be done autonomously. To show that autonomous navigation is possible, we investigated it in the hardest place to do it - inside the beating heart. We created a robotic catheter that can navigate through the blood-filled heart using wall-following algorithms inspired by positively thigmotactic animals. The catheter employs haptic vision, a hybrid sense using imaging for both touch-based surface identification and force sensing, to accomplish wall following inside the blood-filled heart. Through in vivo animal experiments, we demonstrate that the performance of an autonomously-controlled robotic catheter rivals that of an experienced clinician. Autonomous navigation is a fundamental capability on which more sophisticated levels of autonomy can be built, e.g., to perform a procedure. Similar to the role of automation in fighter aircraft, such capabilities can free the clinician to focus on the most critical aspects of the procedure while providing precise and repeatable tool motions independent of operator experience and fatigue.
| S-EPMC6693882 | biostudies-literature
Project description:This paper adds on to the on-going efforts to provide more autonomy to space robots and introduces the concept of programming by demonstration or imitation learning for trajectory planning of manipulators on free-floating spacecraft. A redundant 7-DoF robotic arm is mounted on small spacecraft dedicated for debris removal, on-orbit servicing and assembly, autonomous and rendezvous docking. The motion of robot (or manipulator) arm induces reaction forces on the spacecraft and hence its attitude changes prompting the Attitude Determination and Control System (ADCS) to take large corrective action. The method introduced here is capable of finding the trajectory that minimizes the attitudinal changes thereby reducing the load on ADCS. One of the critical elements in spacecraft trajectory planning and control is the power consumption. The approach introduced in this work carry out trajectory learning offline by collecting data from demonstrations and encoding it as a probabilistic distribution of trajectories. The learned trajectory distribution can be used for planning in previously unseen situations by conditioning the probabilistic distribution. Hence almost no power is required for computations after deployment. Sampling from a conditioned distribution provides several possible trajectories from the same start to goal state. To determine the trajectory that minimizes attitudinal changes, a cost term is defined and the trajectory which minimizes this cost is considered the optimal one.
| S-EPMC8130759 | biostudies-literature
Project description:We consider the problem of autonomous acquisition of manipulation skills where problem-solving strategies are initially available only for a narrow range of situations. We propose to extend the range of solvable situations by autonomous play with the object. By applying previously-trained skills and behaviors, the robot learns how to prepare situations for which a successful strategy is already known. The information gathered during autonomous play is additionally used to train an environment model. This model is exploited for active learning and the generation of novel preparatory behaviors compositions. We apply our approach to a wide range of different manipulation tasks, e.g., book grasping, grasping of objects of different sizes by selecting different grasping strategies, placement on shelves, and tower disassembly. We show that the composite behavior generation mechanism enables the robot to solve previously-unsolvable tasks, e.g., tower disassembly. We use success statistics gained during real-world experiments to simulate the convergence behavior of our system. Simulation experiments show that the learning speed can be improved by around 30% by using active learning.
| S-EPMC7806109 | biostudies-literature
Project description:The ability to handle single molecules as effectively as macroscopic building blocks would enable the construction of complex supramolecular structures inaccessible to self-assembly. The fundamental challenges obstructing this goal are the uncontrolled variability and poor observability of atomic-scale conformations. Here, we present a strategy to work around both obstacles and demonstrate autonomous robotic nanofabrication by manipulating single molecules. Our approach uses reinforcement learning (RL), which finds solution strategies even in the face of large uncertainty and sparse feedback. We demonstrate the potential of our RL approach by removing molecules autonomously with a scanning probe microscope from a supramolecular structure. Our RL agent reaches an excellent performance, enabling us to automate a task that previously had to be performed by a human. We anticipate that our work opens the way toward autonomous agents for the robotic construction of functional supramolecular structures with speed, precision, and perseverance beyond our current capabilities.
| S-EPMC7467688 | biostudies-literature
Project description:Complex contact-rich insertion is a ubiquitous robotic manipulation skill and usually involves nonlinear and low-clearance insertion trajectories as well as varying force requirements. A hybrid trajectory and force learning framework can be utilized to generate high-quality trajectories by imitation learning and find suitable force control policies efficiently by reinforcement learning. However, with the mentioned approach, many human demonstrations are necessary to learn several tasks even when those tasks require topologically similar trajectories. Therefore, to reduce human repetitive teaching efforts for new tasks, we present an adaptive imitation framework for robot manipulation. The main contribution of this work is the development of a framework that introduces dynamic movement primitives into a hybrid trajectory and force learning framework to learn a specific class of complex contact-rich insertion tasks based on the trajectory profile of a single task instance belonging to the task class. Through experimental evaluations, we validate that the proposed framework is sample efficient, safer, and generalizes better at learning complex contact-rich insertion tasks on both simulation environments and on real hardware.
| S-EPMC8787218 | biostudies-literature
Project description:The characterization of observables, expressed via Hermitian operators, is a crucial task in quantum mechanics. For this reason, an eigensolver is a fundamental algorithm for any quantum technology. In this work, we implement a semi-autonomous algorithm to obtain an approximation of the eigenvectors of an arbitrary Hermitian operator using the IBM quantum computer. To this end, we only use single-shot measurements and pseudo-random changes handled by a feedback loop, reducing the number of measures in the system. Due to the classical feedback loop, this algorithm can be cast into the reinforcement learning paradigm. Using this algorithm, for a single-qubit observable, we obtain both eigenvectors with fidelities over 0.97 with around 200 single-shot measurements. For two-qubits observables, we get fidelities over 0.91 with around 1500 single-shot measurements for the four eigenvectors, which is a comparatively low resource demand, suitable for current devices. This work is useful to the development of quantum devices able to decide with partial information, which helps to implement future technologies in quantum artificial intelligence.
| S-EPMC8192530 | biostudies-literature
Project description:Autism spectrum condition (ASC) is primarily diagnosed by behavioural symptoms including social, sensory and motor aspects. Although stereotyped, repetitive motor movements are considered during diagnosis, quantitative measures that identify kinematic characteristics in the movement patterns of autistic individuals are poorly studied, preventing advances in understanding the aetiology of motor impairment, or whether a wider range of motor characteristics could be used for diagnosis. The aim of this study was to investigate whether data-driven machine learning based methods could be used to address some fundamental problems with regard to identifying discriminative test conditions and kinematic parameters to classify between ASC and neurotypical controls. Data was based on a previous task where 16 ASC participants and 14 age, IQ matched controls observed then imitated a series of hand movements. 40 kinematic parameters extracted from eight imitation conditions were analysed using machine learning based methods. Two optimal imitation conditions and nine most significant kinematic parameters were identified and compared with some standard attribute evaluators. To our knowledge, this is the first attempt to apply machine learning to kinematic movement parameters measured during imitation of hand movements to investigate the identification of ASC. Although based on a small sample, the work demonstrates the feasibility of applying machine learning methods to analyse high-dimensional data and suggest the potential of machine learning for identifying kinematic biomarkers that could contribute to the diagnostic classification of autism.
| S-EPMC5558936 | biostudies-literature
Project description:The navigation of bees and ants from hive to food and back has captivated people for more than a century. Recently, the Navigation by Scene Familiarity Hypothesis (NSFH) has been proposed as a parsimonious approach that is congruent with the limited neural elements of these insects' brains. In the NSFH approach, an agent completes an initial training excursion, storing images along the way. To retrace the path, the agent scans the area and compares the current scenes to those previously experienced. By turning and moving to minimize the pixel-by-pixel differences between encountered and stored scenes, the agent is guided along the path without having memorized the sequence. An important premise of the NSFH is that the visual information of the environment is adequate to guide navigation without aliasing. Here we demonstrate that an image landscape of an indoor setting possesses ample navigational information. We produced a visual landscape of our laboratory and part of the adjoining corridor consisting of 2816 panoramic snapshots arranged in a grid at 12.7-cm centers. We show that pixel-by-pixel comparisons of these images yield robust translational and rotational visual information. We also produced a simple algorithm that tracks previously experienced routes within our lab based on an insect-inspired scene familiarity approach and demonstrate that adequate visual information exists for an agent to retrace complex training routes, including those where the path's end is not visible from its origin. We used this landscape to systematically test the interplay of sensor morphology, angles of inspection, and similarity threshold with the recapitulation performance of the agent. Finally, we compared the relative information content and chance of aliasing within our visually rich laboratory landscape to scenes acquired from indoor corridors with more repetitive scenery.
| S-EPMC4847926 | biostudies-literature
Project description:This paper presents an autonomous navigation system for cost-effective magnetic-assisted colonoscopy, employing force-based sensors, an actuator, a proportional-integrator controller and a real-time heuristic searching method. The force sensing system uses load cells installed between the robotic arm and external permanent magnets to derive attractive force data as the basis for real-time surgical safety monitoring and tracking information to navigate the disposable magnetic colonoscope. The average tracking accuracy on magnetic field navigator (MFN) platform in x-axis and y-axis are 1.14 ± 0.59 mm and 1.61 ± 0.45 mm, respectively, presented in mean error ± standard deviation. The average detectable radius of the tracking system is 15 cm. Three simulations of path planning algorithms are presented and the learning real-time A* (LRTA*) algorithm with our proposed directional heuristic evaluation design has the best performance. It takes 75 steps to complete the traveling in unknown synthetic colon map. By integrating the force-based sensing technology and LRTA* path planning algorithm, the average time required to complete autonomous navigation of a highly realistic colonoscopy training model on the MFN platform is 15 min 38 s and the intubation rate is 83.33%. All autonomous navigation experiments are completed without intervention by the operator.
| S-EPMC8363733 | biostudies-literature
Project description:Background: The incidence of silent cerebral embolisms (SCEs) has been documented after pulmonary vein isolation using different ablation technologies; however, it is unreported in patients undergoing with atrial fibrillation (AF) ablation using Robotic Magnetic Navigation (RMN). The purpose of this prospective study was to investigate the incidence, risk predictors and probable mechanisms of SCEs in patients with AF ablation and the potential impact of RMN on SCE rates. Methods and Results: We performed a prospective study of 166 patients with paroxysmal or persistent AF who underwent pulmonary vein isolation. Patients were divided into RMN group (n = 104) and manual control (MC) group (n = 62), and analyzed for their demographic, medical, echocardiographic, and risk predictors of SCEs. All patients underwent cerebral magnetic resonance imaging within 48 h before and after the ablation procedure to assess cerebral embolism. The incidence and potential risk factors of SCEs were compared between the two groups. There were 26 total cases of SCEs in this study, including 6 cases in the RMN group and 20 cases in the MC group. The incidences of SCEs in the RMN group and the MC group were 5.77 and 32.26%, respectively (X2 = 20.63 P < 0.05). Univariate logistic regression analysis demonstrated that ablation technology, CHA2DS2-VASc score, history of cerebrovascular accident/transient ischemic attack, and low ejection fraction were significantly associated with SCEs, and multivariate logistic regression analysis showed that MC ablation was the only independent risk factor of SCEs after an AF ablation procedure. Conclusions: Ablation technology, CHA2DS2-VASc score, history of cerebrovascular accident/transient ischemic attack, and low ejection fraction are associated with SCEs. However, ablation technology is the only independent risk factor of SCEs and RMN can significantly reduce the incidence of SCEs resulting from AF ablation. Clinical Trial Registration: ChiCTR2100046505.
| S-EPMC8671737 | biostudies-literature