Search

The biological world serves as a vast reservoir of inspiration for human innovation, particularly in the realm of robotics designed to navigate intricate granular environments. Among these creatures adept at burrowing, the mole stands out due to its exceptional body structure and unparalleled efficiency, surpassing most engineering burrowing systems. Consequently, the mole serves as an ideal model for designing highly efficient burrowing robots. This study introduces a mole‐inspired robot burrowing with forelimbs, specifically designed for planetary soil exploration. By closely examining the distinctive body morphology of moles, a forelimb burrowing mechanism is devised through biomimetic mapping, and its kinematics is thoroughly analyzed. A robot prototype is developed and an experimental setup is constructed to evaluate its burrowing performance. A series of tests are conducted to assess the capabilities of the robot, including forelimb burrowing, robot crawling, and robot burrowing. The results demonstrate that the proposed mole‐inspired burrowing robot is capable of crawling and burrowing to a certain depth using its forelimbs. Although it exhibits some upward displacement, this issue can be mitigated by modifying the head configuration and adjusting the forelimb posture to effectively overcome the vertical stress and lift force exerted by granular soils due to intensity gradient.

For robots in human environments, learning complex and demanding interaction skills from humans and responding quickly to human motions are highly desirable. A common challenge for interaction tasks is that the robot has to satisfy both the task space and the joint space constraints on its motion trajectories in real time. Few studies have addressed the issue of hyperspace constraints in human-robot interaction, whereas researchers have investigated it in robot imitation learning. In this work, we propose a method of dual-space feature fusion to enhance the accuracy of the inferred trajectories in both task space and joint space; then, we introduce a linear mapping operator (LMO) to map the inferred task space trajectory to a joint space trajectory. Finally, we combine the dual-space fusion, LMO, and phase estimation into a unified probabilistic framework. We evaluate our dual-space feature fusion capability and real-time performance in the task of a robot following a human-handheld object and a ball-hitting experiment. Our inference accuracy in both task space and joint space is superior to standard Interaction Primitives (IP) which only use single-space inference (by more than 33%); the inference accuracy of the second order LMO is comparable to the kinematic-based mapping method, and the computation time of our unified inference framework is reduced by 54.87% relative to the comparison method.

To promote operational intelligence, improve surface quality, and reduce manpower dependence, a novel high-bandwidth end-effector with active force control for robotic polishing was proposed. Using this end-effector as a mini robot, a macro-mini robot for polishing processing was constructed, in which the macro robot provides posture control during polishing operations, whereas the mini-robot provides constant force control. By minimizing the inertia along the spindle in this configuration, the end-effector obtains a force control bandwidth of 200 Hz. Through a series of comparative experiments with different contact forces and feed rates, the proposed design was proven to have a smaller overshoot, a faster response, and a shorter settling time than the conventional method based on macro robot (KUKA iiwa) controlled force. The roughness of the workpiece reached $0.4~\mu \text{m}$ after polishing with the macro-mini robot, indicating the efficiency of this end-effector in high-precision material removal and surface polishing operations.

Electroadhesive grippers can be used to pick up a wide range of materials, and those with variable stiffness functionality can increase load capacity and strength. This paper proposes an electroadhesive gripper (VSEAF) with variable stiffness function and a simple construction based on low melting point alloys (LMPAs) with active form adaptation through pneumatic driving. Resistance wires provide active changing stiffness. For a case study, a three-fingered gripper was designed with three electroadhesive fingers of varied stiffness. It is envisaged that these electroadhesive grippers with variable stiffness would extend the preparation process and boost the use of electroadhesion in soft robot applications.

In this paper, we proposed a Regular Tetrahedral Array (RTA) to cope with various types of sensors expected in Ultra-Wideband (UWB) localization requiring all-directional detection capability and high accuracy, such as indoor Internet-of-Things (IoT) devices at diverse locations, UAVs performing aerial navigation, collision avoidance and takeoff/landing guidance. The RTA is deployed with four synchronized Ultra-Wideband (UWB) transceivers on its vertexes and configured with arbitrary aperture. An all-directional DOA estimation algorithm using combined TDoA and wrapped PDoA was conducted. The 3D array RTA was decomposed into four planar subarrays solved as phased Uniform Circular Array (UCA) respectively. A new cost function based on geometric identical and variable neighborhood search strategy using TDoA information was proposed for ambiguity resolution. The results of simulation and numerical experiments demonstrated excellent performance of the proposed RTA and corresponding algorithm.

Robot introspection aids robots to understand what they do and how they do it. Previous robot introspection techniques have often used parametric hidden Markov models or supervised learning techniques, implying that the number of hidden states or classes is defined a priori and fixed through the entire modeling process. Fixed parameterizations limit the modeling power of a process to properly encode the data. Furthermore, first-order Markov models are limited in their ability to model complex data sequences that represent highly dynamic behaviors as they assume observations are conditionally independent given the state. In this work, we contribute a Bayesian nonparametric autoregressive Hidden Markov model for the monitoring of robot contact tasks, which are characterized by complex dynamical data that are hard to model. We used a nonparametric prior that endows our hidden Markov models with an unbounded number of hidden states for a given robot skill (or subtask). We use a hierarchical Dirichlet stochastic process prior to learn an hidden Markov model with a switching vector autoregressive observation model of wrench signatures and end-effector pose for the manipulation contact tasks. The proposed scheme monitors both nominal skill execution and anomalous behaviors. Two contact tasks are used to measure the effectiveness of our approach: (i) a traditional pick-and-place task composed of four skills and (ii) a cantilever snap assembly task (also composed of four skills). The modeling performance or our approach was compared with other methods, and classification accuracy measures were computed for skill and anomaly identification. The hierarchical Dirichlet stochastic process prior to learn an hidden Markov model with a switching vector autoregressive observation model was shown to have excellent process monitoring performance with higher identification rates and monitoring ability.

A variety of soft robots with prospective applications has been developed in recent years. As a key component of a soft robot, the soft actuator plays a critical role and hence must be designed carefully according to application requirements. The soft body may deform in undesired directions if no restraint is endued, due to the isotropy of the pure soft material. For some soft robots such as an inchworm-like biped climbing robot, the actuation direction must be constrained with the appropriate structure design of the soft actuator. This study proposes a pneumatic soft actuator (PSA) to achieve pure in-plane bending motion with anisotropic soft and rigid restraints. The in-plane bending pneumatic soft actuator (2D-PSA) is developed with a composite structure where a metal hinge belt is embedded into the soft material. The design method, material choice, and fabrication process are presented in detail in this paper. Tests are conducted to measure the actuating performance of 2D-PSA in terms of the relationship between the bending angle or force and the input air pressure. Dynamic response is also measured with a laser tracker. Furthermore, a comparative experiment is carried out between the presented 2D-PSA and a general PSA, with results verifying the effectiveness of the presented 2D-PSA. A robot consisting of two serially-connected 2D-PSAs and three pneumatic suckers, which can climb on a flat surface mimicking a snake’s locomotion, is developed as an application demo of the presented 2D-PSA. Its locomotion capability presents the in-plane performance and mobility of 2D-PSA.

Robot introspection is expected to greatly aid longer-term autonomy of autonomous manipulation systems. By equipping robots with abilities that allow them to assess the quality of their sensory data, robots can detect and classify anomalies and recover appropriately from common anomalies. This work builds on our previous Sense-Plan-Act-Introspect-Recover (SPAIR) system. We introduce an improved anomaly detector that exploits latent states to monitor anomaly occurrence when robots collaborate with humans in shared workspaces, but also present a multiclass classifier that is activated with anomaly detection. Both implementations are derived from Bayesian non-parametric methods with strong modeling capabilities for learning and inference of multivariate time series with complex and uncertain behavior patterns. In particular, we explore the use of a hierarchical Dirichlet stochastic process prior to learning a Hidden Markov Model (HMM) with a switching vector auto-regressive observation model (sHDP-VAR-HMM). The detector uses a dynamic log-likelihood threshold that varies by latent state for anomaly detection and the anomaly classifier is implemented by calculating the cumulative log-likelihood of testing observation based on trained models. The purpose of our work is to equip the robot with anomaly detection and anomaly classification for the full set of skills associated with a given manipulation task. We consider a human–robot cooperation task to verify our work and measure the robustness and accuracy of each skill. Our improved detector succeeded in detecting 136 common anomalies and 368 nominal executions with a total accuracy of 91.0%. An overall anomaly classification accuracy of 97.1% is derived by performing the anomaly classification on an anomaly dataset that consists of 7 kinds of detected anomalies from a total of 136 anomalies samples.

Reliability of visual tracking and mapping is a challenging problem in robotics research, and it limits the promotion of vision-based mobile robot applications to a great extent. In this paper, we propose to improve the reliability of visual exploration in terms of its fault tolerance. Three modules are involved in our visual exploration system: visual localization and mapping, active controller and termination condition. High maintainability of mapping is obtained by the submap-based visual mapping module, persistent driving is achieved by a semantic segmentation based active controller, and robustness of re-localization is guaranteed by a novel completeness evaluation method in the termination condition. All the modules are integrated tightly for maintaining mapping and improving visual tracking. The system is verified with simulations and real world experiments, and all the solutions to fault tolerance are verified to overcome the failure conditions of visual tracking and mapping.

Biped climbing robots (BiCRs) can overcome obstacles and perform transition easily thanks to their superior flexibility. However, to move in a complex truss environment, grips from the original point to the destination, as a sequence of anchor points along the route, are indispensable. In this paper, a grip planning method is presented for BiCRs generating optimal collision-free grip sequences, as a continuation of our previous work on global path planning. A mathematic model is firstly built up for computing the operational regions for negotiating obstacle members. Then a grip optimization model is proposed to determine the grips within each operational region for transition or for obstacle negotiation. This model ensures the total number of required climbing steps is minimized and the transition grips are with good manipulability. Lastly, the entire grip sequence satisfying the robot kinematic constraint is generated by a gait interpreter. Simulations are conducted with our self-developed biped climbing robot (Climbot), to verify the effectiveness and efficiency of the proposed methodology.

In kernel methods, Nyström approximation is a popular way of calculating out-of-sample extensions and can be further applied to large-scale data clustering and classification tasks. Given a new data point, Nyström employs its empirical affinity vector, k, for calculation. This vector is assumed to be a proper measurement of the similarity between the new point and the training set. In this paper, we suggest replacing the affinity vector by its projections on the leading eigenvectors learned from the training set, i.e., using k*=∑i=1ckTuiui instead, where ui is the i-th eigenvector of the training set and c is the number of eigenvectors used, which is typically equal to the number of classes designed by users. Our work is motivated by the constraints that in kernel space, the kernel-mapped new point should (a) also lie on the unit sphere defined by the Gaussian kernel and (b) generate training set affinity values close to k. These two constraints define a Quadratic Optimization Over a Sphere (QOOS) problem. In this paper, we prove that the projection on the leading eigenvectors, rather than the original affinity vector, is the solution to the QOOS problem. The experimental results show that the proposed replacement of k by k* slightly improves the performance of the Nyström approximation. Compared with other affinity matrix modification methods, our k* obtains comparable or higher clustering performance in terms of accuracy and Normalized Mutual Information (NMI).

Biped climbing robots are considered good assistants and (or) substitutes for human workers carrying out high-rise truss-associated routine tasks. Flexible locomotion on three-dimensional complex trusses is a fundamental skill for these robots. In particular, the capability to transit from one structural member to another is paramount for switching objects to be climbed upon. In this paper, we study member-to-member transition and its utility in global path searching for biped climbing robots. To compute operational regions for transition, hierarchical inspection of safety, reachability, and accessibility of grips is taken into account. A novel global path rapid determination approach is subsequently proposed based on the transition analysis. This scheme is efficient for finding feasible routes with respect to the overall structural environment, which also benefits the subsequent grip and motion planning. Simulations are conducted with Climbot, our self-developed biped climbing robot, to verify the efficiency of the presented method. Results show that our proposed method is able to accurately determine the operational region for transition within tens of milliseconds and can obtain global paths within seconds in general.