Soft robots have a myriad of potentials because their intrinsically compliant bodies, enabling safe interactions with humans and adaptability to unpredictable environments. However, most them limited actuation speeds, require complex control systems, lack sensing capabilities. To address these challenges, here we geometrically design class metacaps whose rich nonlinear mechanical behaviors can be harnessed create soft unprecedented functionalities. Specifically, demonstrate sensor-less...

People who suffer from hearing impairment caused by illness, age or extremely noisy environments are constantly in danger of being hit knocked down fast moving objects behind them when they have no companion augmented sensory system to warn them. In this paper, we propose the General Moving Object Alarm System (GMOAS), a focused on aiding safe mobility people under these circumstances. The GMOAS is wearable haptic device that consists two main subsystems: (i) object monitoring subsystem uses...

Coordination is essential in the design of dynamic control strategies for multi-arm robotic systems. Given complexity task and dexterity system, coordination constraints can emerge from different levels planning control. Primarily, one must consider task-space coordination, where robots coordinate with each other, an object or a target interest. also necessary joint space, as should avoid self-collisions at any time. We provide such joint-space by introducing centralized inverse kinematics...

With the introduction of new depth-sensing technologies, interactive hand-gesture devices (such as smart televisions and displays) have been rapidly emerging. However, given lack a common vocabulary, most control commands are device-specific, burdening user into learning different vocabularies for devices. In order hand gestures to become natural communication users with devices, standardized vocabulary is necessary. Recently, researchers approached this issue by conducting studies that...

As prominent real-time safety-critical reactive control techniques, Control Barrier Function Quadratic Programs (CBF-QPs) work for affine systems in general but result local minima the generated trajectories and consequently cannot ensure convergence to goals. Contrarily, Modulation of Dynamical Systems (Mod-DSs), including normal, reference, on-manifold Mod-DS, achieve obstacle avoidance with few even no have trouble optimally minimizing difference between constrained unconstrained...

In this letter, we propose a real-time self-collision avoidance approach for whole-body humanoid robot control. To achieve this, learn the feasible regions of control in humanoid's joint space as smooth boundary functions. Collision-free motions are generated online by treating learned functions constraints Quadratic Program based Inverse Kinematic solver. As geometrical complexity grows with number degrees-of-freedom (DoF), learning computationally efficient and accurate is challenging. We...

This paper introduces a hierarchical framework that is capable of learning complex sequential tasks from human demonstrations through kinesthetic teaching, with minimal intervention. Via an automatic task segmentation and action primitive discovery algorithm, we are able to learn both the high-level decomposition (into primitives), as well low-level motion parameterizations for each action, in fully integrated framework. In order reach desired goal, encode metric based on evolution...

In this letter, we present an approach for learning a neural implicit signed distance function expressed in joint space coordinates, that efficiently computes distance-to-collisions arbitrary robotic manipulator configurations. Computing such distances is long standing problem robotics as approximate representations of the robot and environment geometry can lead to overly conservative constraints, numerical instabilities expensive computations – limiting real-time reactive control task...

This paper proposes a method to assess the overall fatigue of human body movement. First all, according previous research regarding localized muscular fatigue, linear relation is assumed between mean frequency and working time when muscle experiencing fatigue. assumption verified with rigorous statistical analysis. Based on this proven linearity, simplified as model. Furthermore, considered dynamic process and, hence, levels are tracked by updating parameters most current surface...

Coordinated control strategies for multi-robot systems are necessary tasks that cannot be executed by a single robot.This encompasses where the workspace of robot is too small or load heavy one to handle.Using multiple robots makes task feasible extending and/or increase payload overall robotic system.In this paper, we consider two instances such tasks: co-worker scenario in which human hands over large object robot; intercepting flying object.The problem made difficult as pick-up/intercept...

State-dependent dynamical systems (DSs) offer adaptivity, reactivity, and robustness to perturbations in motion planning physical human–robot interaction tasks. Learning DS-based plans from non-linear reference trajectories is an active research area robotics. Most approaches focus on learning DSs that can (i) accurately mimic the demonstrated motion, while (ii) ensuring convergence target, i.e., they are globally asymptotically (or exponentially) stable. When subject perturbations, a...

Ensuring human safety without unnecessarily impacting task efficiency during human-robot interactive manipulation tasks is a critical challenge.In this work, we formally define physical as collision avoidance or safe impact in the event of collision.We developed motion planner that theoretically guarantees safety, with high probability, under uncertainty dynamic models.Our two-pronged definition able to unlock planner's potential finding efficient plans even when nearly impossible.The...

This paper introduces a hierarchical framework that is capable of learning complex sequential tasks from human demonstrations through kinesthetic teaching, with minimal intervention. Via an automatic task segmentation and action primitive discovery algorithm, we are able to learn both the high-level decomposition (into primitives), as well low-level motion parameterizations for each action, in fully integrated framework. In order reach desired goal, encode metric based on evolution...

In this letter, we propose an asymptotically stable joint-space dynamical system (DS) that captures desired behaviors in while converging toward a task-space attractor both position and orientation. To encode meeting the stability criteria, DS constructed as linear parameter varying combining different behavior synergies provide method for learning these synergy matrices from demonstrations. Specifically, use dimensionality reduction to find low-dimensional embedding space modulating joint...

With the introduction of new depth sensing technologies, interactive hand-gesture devices are rapidly emerging. However, hand-gestures used in these do not follow a common vocabulary, making certain control command device-specific. In this paper we present an initial effort to create standardized vocabulary for next generation television applications. We conduct user-elicitation study using survey order define specific commands, such as Volume up/down, Menu open/close, etc. This is entirely...

Redundant muscle-driven arms have numerous advantages, such as increased robustness, ability for load distribution, impedance change etc. However, controlling a arm is difficult task. This mainly due to its redundancy, specially when the muscle force required follow certain output constraints and fulfill optimization objectives. In this paper, new method muscle-like systems proposed. By considering both joint acceleration contributions, set of linear equations was constructed. Driving...

In this paper we discuss how the combination of modern technologies in "big data" storage and management, knowledge representation processing, cloud-based computation, web technology can help robotics community to establish strengthen an open research discipline. We describe made demonstrator a EU project review openly available community. Specifically, recorded episodic memories with rich semantic annotations during pizza preparation experiment autonomous robot manipulation. Afterwards,...

Dynamical system (DS) based motion planning offers collision-free motion, with closed-loop reactivity thanks to their analytical expression. It ensures that obstacles are not penetrated by reshaping a nominal DS through matrix modulation, which is constructed using continuously differentiable obstacle representations. However, state-of-the-art approaches may suffer from local minima induced non-convex obstacles, thus failing scale complex, high-dimensional joint spaces. On the other hand,...

The Linear Parameter Varying Dynamical System (LPV-DS) is an effective approach that learns stable, time-invariant motion policies using statistical modeling and semi-definite optimization to encode complex motions for reactive robot control. Despite its strengths, the LPV-DS learning faces challenges in achieving high model accuracy without compromising computational efficiency. To address this, we introduce Directionality-Aware Mixture Model (DAMM), a novel applies Riemannian metric on...

In this work, we present a novel, reactive, modulated control strategy based on dynamical systems (DS) for planning in the context of multiple non-convex obstacles. Our DS modulation leverages an on-manifold methodology and provides several methods real-time navigation around We introduce sample-based obstacle representation complex, obstacles, as well projection-based method representing surfaces such tables, cylinders, ellipsoids. These representations can be combined to represent...

In this paper, we introduce the From Sense to Print system. It is a system where 3D sensing device connected cloud used reconstruct an object or human and generate CAD models which are sent automatically printer. other words, ready-to-print of objects without manual intervention in processing pipeline. Our proposed validated with experimental prototype using Kinect sensor as device, KinectFusion algorithm our reconstruction fused deposition modeling (FDM) order for pipeline be automatic,...