Robots have surpassed humans in terms of strength and precision, yet humans retain an unparalleled ability for decision-making in the face of unpredictable disturbances. This article aims to combine the strengths of both entities within a singular task: human motion guidance under strict geometric constraints, particularly adhering to predetermined paths. To tackle this challenge, a modular haptic guidance law is proposed that takes the human-applied wrench as an input. Using an auxiliary variable called phase, the generated desired motion is guaranteed to consistently adhere to the constraint path. The guidance policy can be generalized into physically interpretable terms, adjustable either prior to initiating the task or dynamically while the task is in progress. An illustrative guidance adaptation policy is showcased that takes into account the human's manipulability. Passivity analysis is used to ensure overall system stability. Experiments, including a 20-participant user study, explore various aspects of the approach in practice.

Embodied reasoning systems integrate robotic hardware and cognitive processes to perform complex tasks, typically in response to a natural language query about a specific physical environment. This usually involves changing the belief about the scene or physically interacting and changing the scene (e.g. sort the objects from lightest to heaviest). In order to facilitate the development of such systems we introduce a new modular Closed Loop Interactive Embodied Reasoning (CLIER) approach that takes into account the measurements of non-visual object properties, changes in the scene caused by external disturbances as well as uncertain outcomes of robotic actions. CLIER performs multi-modal reasoning and action planning and generates a sequence of primitive actions that can be executed by a robot manipulator. Our method operates in a closed loop, responding to changes in the environment. Our approach is developed with the use of MuBle simulation environment and tested in$\mathbf{1 0}$interactive benchmark scenarios. We extensively evaluate our reasoning approach in simulation and in real-world manipulation tasks with a success rate above$\mathbf{7 6 \%}$and 64%, respectively.

For safe and effective operation of humanoid robots in human-populated environments, the problem of commanding a large number of degrees of freedom (DoFs) while simultaneously considering dynamic obstacles and human proximity has still not been solved. In this article, we present a new reactive motion controller that commands two arms of a humanoid robot and three torso joints (17 DoF in total). We formulate a quadratic program that seeks joint velocity commands respecting multiple constraints while minimizing the magnitude of the velocities. We introduce a new unified treatment of obstacles that dynamically maps visual and proximity (precollision) and tactile (postcollision) obstacles as additional constraints to the motion controller, in a distributed fashion over the surface of the upper body of the iCub robot (with 2000 pressure-sensitive receptors). This results in a bioinspired controller that: first, gives rise to a robot with whole-body visuo-tactile awareness, resembling peripersonal space representations, and, second, produces human-like minimum jerk movement profiles. The controller was extensively experimentally validated, including a physical human–robot interaction scenario.

Robots have surpassed humans in terms of strength and precision, yet humans retain an unparalleled ability for decision-making in the face of unpredictable disturbances. This article aims to combine the strengths of both entities within a singular task: human motion guidance under strict geometric constraints, particularly adhering to predetermined paths. To tackle this challenge, a modular haptic guidance law is proposed that takes the human-applied wrench as an input. Using an auxiliary variable called phase, the generated desired motion is guaranteed to consistently adhere to the constraint path. It is demonstrated how the guidance policy can be generalized into physically interpretable terms, adjustable either prior to initiating the task or dynamically while the task is in progress. Additionally, an illustrative guidance adaptation policy is showcased that takes into account the human's manipulability. Leveraging passivity analysis, potential sources of instability are pinpointed, and subsequently, overall system stability is ensured by incorporating an augmented virtual energy tank. Lastly, a comprehensive set of experiments, including a 20-participant user study, explores various aspects of the approach in practice, encompassing both technical and usability considerations.

This work presents a framework for automatically extracting physical object properties, such as material composition, mass, volume, and stiffness, through robot manipulation and a database of object measurements. The framework involves exploratory action selection to maximize learning about objects on a table. A Bayesian network models conditional dependencies between object properties, incorporating prior probability distributions and uncertainty associated with measurement actions. The algorithm selects optimal exploratory actions based on expected information gain and updates object properties through Bayesian inference. Experimental evaluation demonstrates effective action selection compared to a baseline and correct termination of the experiments if there is nothing more to be learned. The algorithm proved to behave intelligently when presented with trick objects with material properties in conflict with their appearance. The robot pipeline integrates with a logging module and an online database of objects, containing over 24,000 measurements of 63 objects with different grippers. All code and data are publicly available, facilitating automatic digitization of objects and their physical properties through exploratory manipulations.

Manipulability analysis is a methodology employed to assess the capacity of an articulated system, at a specific configuration, to produce motion or exert force in diverse directions. The conventional method entails generating a virtual ellipsoid using the system’s configuration and model. Yet, this approach poses challenges when applied to systems such as the human body, where direct access to such information is limited, necessitating reliance on estimations. Any inaccuracies in these estimations can distort the ellipsoid’s configuration, potentially compromising the accuracy of the manipulability assessment. To address this issue, this article extends the standard approach by introducing the concept of the manipulability pseudo-ellipsoid. Through a series of theoretical analyses, simulations, and experiments, the article demonstrates that the proposed method exhibits reduced sensitivity to noise in sensory information, consequently enhancing the robustness of the approach.

Predictive coding, currently a highly influential theory in neuroscience, has not been widely adopted in machine learning yet. In this work, we transform the seminal model of Rao and Ballard (1999) into a modern deep learning framework while remaining maximally faithful to the original schema. The resulting network we propose (PreCNet) is tested on a widely used next-frame video prediction benchmark, which consists of images from an urban environment recorded from a car-mounted camera, and achieves state-of-the-art performance. Performance on all measures (MSE, PSNR, and SSIM) was further improved when a larger training set (2M images from BDD100k) pointed to the limitations of the KITTI training set. This work demonstrates that an architecture carefully based on a neuroscience model, without being explicitly tailored to the task at hand, can exhibit exceptional performance.

In haptic object discrimination, the effect of gripper embodiment, action parameters, and sensory channels has not been systematically studied. We used two anthropomorphic hands and two two-finger grippers to grasp two sets of deformable objects. On the object classification task, we found: 1) among classifiers, SVM on sensory features and LSTM on raw time series performed best across all grippers; 2) faster compression speeds degraded performance; 3) generalization to different grasping configurations was limited; transfer to different compression speeds worked well for the Barrett Hand only. Visualization of the feature spaces using PCA showed that gripper morphology and action parameters were the main source of variance, making generalization across embodiment or grip configurations very difficult. On the highly challenging dataset consisting of polyurethane foams alone, only the Barrett Hand achieved excellent performance. Tactile sensors can thus provide a key advantage even if recognition is based on stiffness rather than shape. The dataset with 24 000 measurements is publicly available.

Two regimes permitting safe physical human-robot interaction, speed and separation monitoring and safety-rated monitored stop, depend on reliable perception of the space surrounding the robot. This can be accomplished by visual sensors (like cameras, RGB-D cameras, LIDARs), proximity sensors, or dedicated devices used in industrial settings like pads that are activated by the presence of the operator. The deployment of a particular solution is often ad hoc and no unified representation of the interaction space or its coverage by the different sensors exists. In this work, we make first steps in this direction by defining the spaces to be monitored, representing all sensor data as information about occupancy and using occupancy-based metrics to calculate how a particular sensor covers the workspace. We demonstrate our approach in two sensor-placement experiments in three static scenes and one experiment in a dynamic scene. The occupancy representation allow the comparison of the effectiveness of various sensor setups. Therefore, this approach can serve as a prototyping tool to establish the sensor setup that provides the most efficient coverage for the given metrics and sensor representations.

For robot manipulation, a complete and accurate object shape is desirable. Here, we present a method that combines visual and haptic reconstruction in a closed-loop pipeline. From an initial viewpoint, the object shape is reconstructed using an implicit surface deep neural network. The location with highest uncertainty is selected for haptic exploration, the object is touched, the new information from touch and a new point cloud from the camera are added, object position is re-estimated and the cycle is repeated. We extend Rustler et al. (2022) by using a new theoretically grounded method to determine the points with highest uncertainty, and we increase the yield of every haptic exploration by adding not only the contact points to the point cloud but also incorporating the empty space established through the robot movement to the object. Additionally, the solution is compact in that the jaws of a closed two-finger gripper are directly used for exploration. The object position is re-estimated after every robot action and multiple objects can be present simultaneously on the table. We achieve a steady improvement with every touch using three different metrics and demonstrate the utility of the better shape reconstruction in grasping experiments on the real robot. On average, grasp success rate increases from 63.3 % to 70.4 % after a single exploratory touch and to 82.7% after five touches. The collected data and code are publicly available (https://osf.io/j6rkd/, https://github.com/ctu-vras/vishac).

We investigated the use of impact sounds generated during exploratory behaviors in a robotic manipulation setup as cues for predicting object surface material and for recognizing individual objects. We collected and make available the YCB-impact sounds dataset which includes over 3,000 impact sounds for the YCB set of everyday objects lying on a table. Impact sounds were generated in three modes: (i) human holding a gripper and hitting, scratching, or dropping the object; (ii) gripper attached to a teleoperated robot hitting the object from the top; (iii) autonomously operated robot hitting the objects from the side with two different speeds. A convolutional neural network is trained from scratch to recognize the object material (steel, aluminium, hard plastic, soft plastic, other plastic, ceramic, wood, paper/cardboard, foam, glass, rubber) from a single impact sound. On the manually collected dataset with more variability in the speed of the action, nearly 60% accuracy for the test set (not presented objects) was achieved. On a robot setup and a stereotypical poking action from top, accuracy of 85% was achieved. This performance drops to 79% if multiple exploratory actions are combined. Individual objects from the set of 75 objects can be recognized with a 79% accuracy. This work demonstrates promising results regarding the possibility of using impact sound for recognition in tasks like single-stream recycling where objects have to be sorted based on their material composition.

Accurately predicting contact between our bodies and environmental objects is paramount to our evolutionary survival. It has been hypothesized that multisensory neurons responding both to touch on the body, and to auditory or visual stimuli occurring near them-thus delineating our peripersonal space (PPS)-may be a critical player in this computation. However, we lack a normative account (i.e., a model specifying how we ought to compute) linking impact prediction and PPS encoding. Here, we leverage Bayesian Decision Theory to develop such a model and show that it recapitulates many of the characteristics of PPS. Namely, a normative model of impact prediction (i) delineates a graded boundary between near and far space, (ii) demonstrates an enlargement of PPS as the speed of incoming stimuli increases, (iii) shows stronger contact prediction for looming than receding stimuli-but critically is still present for receding stimuli when observation uncertainty is non-zero-, (iv) scales with the value we attribute to environmental objects, and finally (v) can account for the differing sizes of PPS for different body parts. Together, these modeling results support the conjecture that PPS reflects the computation of impact prediction, and make a number of testable predictions for future empirical studies.

In this paper, we present an integrated system that includes reasoning from visual and natural language inputs, action and motion planning, executing tasks by a robotic arm, manipulating objects, and discovering their properties. A vision to action module recognises the scene with objects and their attributes and analyses enquiries formulated in natural language. It performs multi-modal reasoning and generates a sequence of simple actions that can be executed by a robot. The scene model and action sequence are sent to a planning and execution module that generates a motion plan with collision avoidance, simulates the actions, and executes them. We use synthetic data to train various components of the system and test on a real robot to show the generalization capabilities. We focus on a tabletop scenario with objects that can be grasped by our embodied agent i.e. a 7DoF manipulator with a two-finger gripper. We evaluate the agent on 60 representative queries repeated 3 times (e.g., ’Check what is on the other side of the soda can’) concerning different objects and tasks in the scene. We perform experiments in a simulated and real environment and report the success rate for various components of the system. Our system achieves up to 80.6% success rate on challenging scenes and queries. We also analyse and discuss the challenges that such an intelligent embodied system faces.

The need to guarantee safety of collaborative robots limits their performance, in particular, their speed and hence cycle time. The standard ISO/TS 15066 defines the Power and Force Limiting operation mode and prescribes force thresholds that a moving robot is allowed to exert on human body parts during impact, along with a simple formula to obtain maximum allowed speed of the robot in the whole workspace. In this work, we measure the forces exerted by two collaborative manipulators (UR10e and KUKA LBR iiwa) moving downward against an impact measuring device. First, we empirically show that the impact forces can vary by more than 100 percent within the robot workspace. The forces are negatively correlated with the distance from the robot base and the height in the workspace. Second, we present a data-driven model, 3D Collision-Force-Map, predicting impact forces from distance, height, and velocity and demonstrate that it can be trained on a limited number of data points. Third, we analyze the force evolution upon impact and find that clamping never occurs for the UR10e. We show that formulas relating robot mass, velocity, and impact forces from ISO/TS 15066 are insufficient—leading both to significant underestimation and overestimation and thus to unnecessarily long cycle times or even dangerous applications. We propose an empirical method that can be deployed to quickly determine the optimal speed and position where a task can be safely performed with maximum efficiency.

With the advent of different electronic skins sensitive to touch and robots composed of soft materials, tactile or haptic human-robot interaction is gaining importance. We designed a highly realistic artificial hand aiming to reproduce human-to-human physical contact through a special morphology imitating flesh and bones and a heating system imitating human body temperature. The mechanical response properties of different finger designs were analyzed and the most mimetic one came very close to a human finger. We designed three experiments with participants using haptic exploration to evaluate the human-likeness of: (1) finger morphologies; (2) complete hands: real human vs. soft and warm artificial hand vs. rubber hand (3) the hand mounted on a manipulator with fixed vs. passive compliant wrist in a handshake scenario. First, participants find the mimetic finger morphology most humanlike. Second, people can reliably distinguish the real human hand, the artificial one, and a rubber hand. In terms of humanlikeness (Anthropomorphism, Animacy, and Likeability), the human hand scores better than the artificial hand which in turn clearly outperforms the rubber hand. The temperature, or "warmth", was rated as the most human-like feature of the artificial hand.

So-called collaborative robots are a current trend in industrial robotics. However, they still face many problems in practical application such as reduced speed to ascertain their collaborativeness. The standards prescribe two regimes: (i) speed and separation monitoring and (ii) power and force limiting, where the former requires reliable estimation of distances between the robot and human body parts and the latter imposes constraints on the energy absorbed during collisions prior to robot stopping. Following the standards, we deploy the two collaborative regimes in a single application and study the performance in a mock collaborative task under the individual regimes, including transitions between them. Additionally, we compare the performance under “safety zone monitoring” with keypoint pair-wise separation distance assessment relying on an RGB-D sensor and skeleton extraction algorithm to track human body parts in the workspace. Best performance has been achieved in the following setting: robot operates at full speed until a distance threshold between any robot and human body part is crossed; then, reduced robot speed per power and force limiting is triggered. Robot is halted only when the operator's head crosses a predefined distance from selected robot parts. We demonstrate our methodology on a setup combining a KUICA LBR iiwa robot, Intel RealSense RGB-D sensor and OpenPose for human pose estimation.

With robots leaving factories and entering less controlled domains, possibly sharing the space with humans, safety is paramount and multimodal awareness of the body surface and the surrounding environment is fundamental. Taking inspiration from peripersonal space representations in humans, we present a framework on a humanoid robot that dynamically maintains such a protective safety zone, composed of the following main components: (i) a human 2D keypoints estimation pipeline employing a deep learning based algorithm, extended here into 3D using disparity; (ii) a distributed peripersonal space representation around the robot»s body parts; (iii) a reaching controller that incorporates all obstacles entering the robot»s safety zone on the fly into the task. Pilot experiments demonstrate that an effective safety margin between the robot»s and the human»s body parts is kept. The proposed solution is flexible and versatile since the safety zone around individual robot and human body parts can be selectively modulated---here we demonstrate stronger avoidance of the human head compared to rest of the body. Our system works in real time and is self-contained, with no external sensory equipment and use of onboard cameras only.

The contribution of the body to cognition and control in natural and artificial agents is increasingly described as "offloading computation from the brain to the body," where the body is said to perform "morphological computation." Our investigation of four characteristic cases of morphological computation in animals and robots shows that the "offloading" perspective is misleading. Actually, the contribution of body morphology to cognition and control is rarely computational, in any useful sense of the word. We thus distinguish (1) morphology that facilitates control, (2) morphology that facilitates perception, and the rare cases of (3) morphological computation proper, such as reservoir computing, where the body is actually used for computation. This result contributes to the understanding of the relation between embodiment and computation: The question for robot design and cognitive science is not whether computation is offloaded to the body, but to what extent the body facilitates cognition and control-how it contributes to the overall orchestration of intelligent behavior.

With robots leaving factory environments and entering less controlled domains, possibly sharing living space with humans, safety needs to be guaranteed. To this end, some form of awareness of their body surface and the space surrounding it is desirable. In this work, we present a unique method that lets a robot learn a distributed representation of space around its body (or peripersonal space) by exploiting a whole-body artificial skin and through physical contact with the environment. Every taxel (tactile element) has a visual receptive field anchored to it. Starting from an initially blank state, the distance of every object entering this receptive field is visually perceived and recorded, together with information whether the object has eventually contacted the particular skin area or not. This gives rise to a set of probabilities that are updated incrementally and that carry information about the likelihood of particular events in the environment contacting a particular set of taxels. The learned representation naturally serves the purpose of predicting contacts with the whole body of the robot, which is of clear behavioral relevance. Furthermore, we devised a simple avoidance controller that is triggered by this representation, thus endowing a robot with a “margin of safety” around its body. Finally, simply reversing the sign in the controller we used gives rise to simple “reaching” for objects in the robot's vicinity, which automatically proceeds with the most activated (closest) body part.

Calibration continues to receive significant attention in robotics because of its key impact on performance and cost associated with the operation of complex robots. Calibration of kinematic parameters is typically the first mandatory step. To this end, a variety of metrology systems and corresponding algorithms have been described in the literature relying on measurements of the pose of the end-effector using a camera or laser tracking system, or, exploiting constraints arising from contacts of the end-effector with the environment. In this work, we take inspiration from the behavior of infants and certain animals, who are believed to use self-stimulation or self-touch to “calibrate” their body representations, and present a new solution to this problem by letting the robot close the kinematic chain by touching its own body. The robot considered in this paper is sensorized with tactile arrays for a total of about 4200 sensing points. The correspondence between the predicted contact point from existing forward kinematics and the actual position on the robot's `skin' provides sample data that allows refining the kinematic representation (DH parameters). The data collection procedure is automated - self-touch is autonomously executed by the robot - and can be repeated at any time, providing a compact self-calibration system that does not require an external measurement apparatus.

It is an important ability for any mobile robot to be able to estimate its posture and to gauge the distance it traveled. In this paper, we have addressed this problem in a dynamic quadruped robot by combining traditional state estimation methods with machine learning. We have designed and implemented a navigation algorithm for full body state (position, velocity, and attitude) estimation that uses no external reference but relies on multimodal proprioceptive sensory information only. The extended Kalman filter (EKF) was used to provide error estimation and data fusion from two independent sources of information: 1) strapdown mechanization algorithm processing raw inertial data and 2) legged odometry. We have devised a novel legged odometer that combines information from a multimodal combination of sensors (joint and pressure). We have shown our method to work for a dynamic turning gait, and we have also successfully demonstrated how it generalizes to different velocities and terrains. Furthermore, our solution proved to be immune to substantial slippage of the robot's feet.

It is an important ability for any mobile robot to be able to estimate its posture and to gauge the distance it travelled. The information can be obtained from various sources. In this work, we have addressed this problem in a dynamic quadruped robot. We have designed and implemented a navigation algorithm for full body state (position, velocity, and attitude) estimation that does not use any external reference (such as GPS, or visual landmarks). Extended Kalman Filter was used to provide error estimation and data fusion from two independent sources of information: Inertial Navigation System mechanization algorithm processing raw inertial data, and legged odometry, which provided velocity aiding. We present a novel data-driven architecture for legged odometry that relies on a combination of joint sensor signals and pressure sensors. Our navigation system ensures precise tracking of a running robot's posture (roll and pitch), and satisfactory tracking of its position over medium time intervals. We have shown our method to work for two different dynamic turning gaits and on two terrains with significantly different friction. We have also successfully demonstrated how our method generalizes to different velocities.

Fish excel in their swimming capabilities. These result from a dynamic interplay of actuation, passive properties of fish body, and interaction with the surrounding fluid. In particular, fish are able to exploit wakes that are generated by objects in flowing water. A powerful demonstration that this is largely due to passive body properties are studies on dead trout. Inspired by that, we developed a multi joint swimming platform that explores the potential of a passive dynamic mechanism. The platform has one actuated joint only, followed by three passive joints whose stiffness can be changed online, individually, and can be set to an almost arbitrary nonlinear stiffness profile. In a set of experiments, using online optimization, we investigated how the platform can discover optimal stiffness distribution along its body in response to different frequency and amplitude of actuation. We show that a heterogeneous stiffness distribution each joint having a different value outperforms a homogeneous one in producing thrust. Furthermore, different gaits emerged in different settings of the actuated joint. This work illustrates the potential of online adaption of passive body properties, leading to optimized swimming, especially in an unsteady environment.