Traditional IK methods for redundant humanoid manipulators emphasize end-effector (EE) tracking, frequently producing configurations that are valid mechanically but not human-like. We present Human-Like Inverse Kinematics (HL-IK), a lightweight IK framework that preserves EE tracking while shaping whole-arm configurations to appear human-like, without full-body sensing at runtime. The key idea is a learned elbow prior: using large-scale human motion data retargeted to the robot, we train a FiLM-modulated spatio-temporal attention network (FiSTA) to predict the next-step elbow pose from the EE target and a short history of EE-elbow states.This prediction is incorporated as a small residual alongside EE and smoothness terms in a standard Levenberg-Marquardt optimizer, making HL-IK a drop-in addition to numerical IK stacks. Over 183k simulation steps, HL-IK reduces arm-similarity position and direction error by 30.6% and 35.4% on average, and by 42.2% and 47.4% on the most challenging trajectories. Hardware teleoperation on a robot distinct from simulation further confirms the gains in anthropomorphism. HL-IK is simple to integrate, adaptable across platforms via our pipeline, and adds minimal computation, enabling human-like motions for humanoid robots. Project page: https://hl-ik.github.io/

MOMAV (Marco's Omnidirectional Micro Aerial Vehicle) is a multirotor drone that is fully actuated, meaning it can control its orientation independently of its position. MOMAV is also highly symmetrical, making its flight efficiency largely unaffected by its current orientation. These characteristics are achieved by a novel drone design where six rotor arms align with the vertices of an octahedron, and where each arm can actively rotate along its long axis. Various standout features of MOMAV are presented: The high flight efficiency compared to arm configuration of other fully-actuated drones, the design of an original rotating arm assembly featuring slip-rings used to enable continuous arm rotation, and a novel control allocation algorithm based on sequential quadratic programming (SQP) used to calculate throttle and arm-angle setpoints in flight. Flight tests have shown that MOMAV is able to achieve remarkably low mean position/orientation errors of 6.6mm, 2.1° (σ: 3.0mm, 1.0°) when sweeping position setpoints, and 11.8mm, 3.3° (σ: 8.6mm, 2.0°) when sweeping orientation setpoints.

--Wearable devices like exoskeletons are designed to reduce excessive loads on specific joints of the body. Specifically, single-or two-degrees-of-freedom (DOF) upper-body industrial exoskeletons typically focus on compensating for the strain on the elbow and shoulder joints. However, during daily activities, there is no assurance that external loads are correctly aligned with the supported joints. Optimizing work processes to ensure that external loads are primarily (to the extent that they can be compensated by the exoskeleton) directed onto the supported joints can significantly enhance the overall usability of these devices and the ergonomics of their users. Collaborative robots (cobots) can play a role in this optimization, complementing the collaborative aspects of human work. In this study, we propose an adaptive and coordinated control system for the human-cobot-exoskeleton interaction. This system adjusts the task coordinates to maximize the utilization of the supported joints. When the torque limits of the exoskeleton are exceeded, the framework continuously adapts the task frame, redistributing excessive loads to non-supported body joints to prevent overloading the supported ones. We validated our approach in an equivalent industrial painting task involving a single-DOF elbow exoskeleton, a cobot, and four subjects, each tested in four different initial arm configurations with five distinct optimisation weight matrices and two different payloads. Personal use of this material is permitted. ANUAL operations such as packaging [1], assembly [2] and painting [3] are essential in many industries, though they can place a significant strain on the physical health of human workers.

Continuum robots with floating bases demonstrate exceptional operational capabilities in confined spaces, such as those encountered in medical surgeries and equipment maintenance. However, developing low-cost solutions for their motion and planning problems remains a significant challenge in this field. This paper investigates the application of geometric iterative strategy methods to continuum robots, and proposes the algorithm based on an improved two-layer geometric iterative strategy for motion planning. First, we thoroughly study the kinematics and effective workspace of a multi-segment tendon-driven continuum robot with a floating base. Then, generalized iterative algorithms for solving arbitrary-segment continuum robots are proposed based on a series of problems such as initial arm shape dependence exhibited by similar methods when applied to continuum robots. Further, the task scenario is extended to a follow-the-leader task considering environmental factors, and further extended algorithm are proposed. Simulation comparison results with similar methods demonstrate the effectiveness of the proposed method in eliminating the initial arm shape dependence and improving the solution efficiency and accuracy. The experimental results further demonstrate that the method based on improved two-layer geometric iteration can be used for motion planning task of a continuum robot with a floating base, under an average deviation of about 4 mm in the end position, an average orientation deviation of no more than 1 degree, and the reduction of average number of iterations and time cost is 127.4 iterations and 72.6 ms compared with similar methods, respectively.

Inverse problems, i.e., estimating parameters of physical models from experimental data, are ubiquitous in science and engineering. The Bayesian formulation is the gold standard because it alleviates ill-posedness issues and quantifies epistemic uncertainty. Since analytical posteriors are not typically available, one resorts to Markov chain Monte Carlo sampling or approximate variational inference. However, inference needs to be rerun from scratch for each new set of data. This drawback limits the applicability of the Bayesian formulation to real-time settings, e.g., health monitoring of engineered systems, and medical diagnosis. The objective of this paper is to develop a methodology that enables real-time inference by learning the Bayesian inverse map, i.e., the map from data to posteriors. Our approach is as follows. We represent the posterior distribution using a parameterization based on deep neural networks. Next, we learn the network parameters by amortized variational inference method which involves maximizing the expectation of evidence lower bound over all possible datasets compatible with the model. We demonstrate our approach by solving examples a set of benchmark problems from science and engineering. Our results show that the posterior estimates of our approach are in agreement with the corresponding ground truth obtained by Markov chain Monte Carlo. Once trained, our approach provides the posterior parameters of observation just at the cost of a forward pass of the neural network.

This paper studies the problem of finding an anomalous arm in a multi-armed bandit when (a) each arm is a finite-state Markov process, and (b) the arms are restless. Here, anomaly means that the transition probability matrix (TPM) of one of the arms (the odd arm) is different from the common TPM of each of the non-odd arms. The TPMs are unknown to a decision entity that wishes to find the index of the odd arm as quickly as possible, subject to an upper bound on the error probability. We derive a problem instance-specific asymptotic lower bound on the expected time required to find the odd arm index, where the asymptotics is as the error probability vanishes. Further, we devise a policy based on the principle of certainty equivalence, and demonstrate that under a continuous selection assumption and a certain regularity assumption on the TPMs, the policy achieves the lower bound arbitrarily closely. Thus, while the lower bound is shown for all problem instances, the upper bound is shown only for those problem instances satisfying the continuous selection and the regularity assumptions. Our achievability analysis is based on resolving the identifiability problem in the context of a certain lifted countable-state controlled Markov process. Index Terms Odd arm identification, restless multi-armed bandits, controlled Markov process, certainty equivalence, identifiability, anomaly detection, anomaly, anomalous process. Consider a multi-armed bandit in which each arm is a time-homogeneous and ergodic discrete-time Markov process taking values in a common finite state space.

Bayesian optimisation has been successfully applied to a variety of reinforcement learning problems. However, the traditional approach for learning optimal policies in simulators does not utilise the opportunity to improve learning by adjusting certain environment variables: state features that are unobservable and randomly determined by the environment in a physical setting but are controllable in a simulator. This paper considers the problem of finding a robust policy while taking into account the impact of environment variables. We present Alternating Optimisation and Quadrature (ALOQ), which uses Bayesian optimisation and Bayesian quadrature to address such settings. ALOQ is robust to the presence of significant rare events, which may not be observable under random sampling, but play a substantial role in determining the optimal policy. Experimental results across different domains show that ALOQ can learn more efficiently and robustly than existing methods.

Search algorithms such as Rapidly-exploring Random Trees (RRTs) are common in robot programming. Including graphical representations of the output of these algorithms in a robotics framework can make the algorithms more accessible to students, and can also help programmers analyze and account for unexpected results. For this project, we used the Tekkotsu open source robot programming framework, available at Tekkotsu.org. We extended Tekkotsu’s graphical user interface for displaying vision data and maps to also display the output of an RRT search. We created several demos using two types of searches: one from a navigation path planner, and one from an arm path planner. In some cases the search had no solution, and the graphical output helped to illustrate why. This confirms the utility of the RRT visualization for explaining unexpected search results. We expect that this tool will also contribute to improved student understanding of the search algorithm.

Visually-guided arm reaching movements are produced by distributed neural networks within parietal and frontal regions of the cerebral cortex. Experimental data indicate that (I) single neurons in these regions are broadly tuned to parameters of movement; (2) appropriate commands are elaborated by populations of neurons; (3) the coordinated action of neurons can be visualized using a neuronal population vector (NPV). However, the NPV provides only a rough estimate of movement parameters (direction, velocity) and may even fail to reflect the parameters of movement when arm posture is changed. We designed a model of the cortical motor command to investigate the relation between the desired direction of the movement, the actual direction of movement and the direction of the NPV in motor cortex. The model is a two-layer self-organizing neural network which combines broadly-tuned (muscular) proprioceptive and (cartesian) visual information to calculate (angular) motor commands for the initial part of the movement of a two-link arm. The network was trained by motor babbling in 5 positions. Simulations showed that (1) the network produced appropriate movement direction over a large part of the workspace; (2) small deviations of the actual trajectory from the desired trajectory existed at the extremities of the workspace; (3) these deviations were accompanied by large deviations of the NPV from both trajectories. These results suggest the NPV does not give a faithful image of cortical processing during arm reaching movements.

Visually-guided arm reaching movements are produced by distributed neural networks within parietal and frontal regions of the cerebral cortex. Experimental data indicate that (I) single neurons in these regions are broadly tuned to parameters of movement; (2) appropriate commands are elaborated by populations of neurons; (3) the coordinated action of neurons can be visualized using a neuronal population vector (NPV). However, the NPV provides only a rough estimate of movement parameters (direction, velocity) and may even fail to reflect the parameters of movement when arm posture is changed. We designed a model of the cortical motor command to investigate the relation between the desired direction of the movement, the actual direction of movement and the direction of the NPV in motor cortex. The model is a two-layer self-organizing neural network which combines broadly-tuned (muscular) proprioceptive and (cartesian) visual information to calculate (angular) motor commands for the initial part of the movement of a two-link arm. The network was trained by motor babbling in 5 positions. Simulations showed that (1) the network produced appropriate movement direction over a large part of the workspace; (2) small deviations of the actual trajectory from the desired trajectory existed at the extremities of the workspace; (3) these deviations were accompanied by large deviations of the NPV from both trajectories. These results suggest the NPV does not give a faithful image of cortical processing during arm reaching movements.