Search

Fall detection and localization of human operators inside a workspace are major issues in ensuring a safe working environment. Recent research has shown that the perturbations of the radio-frequency (RF) signals commonly adopted for wireless communications can also be used as sensing tools for device-free human motion detection. Device-free RF-based human sensing applications range from tag-less body localization to detection and monitoring of human well-being (e-Health). In this paper, we propose a real-time system for human body motion sensing with special focus on joint body localization and fall detection. The proposed system continuously monitors and processes the RF signals emitted by industry-compliant radio devices operating in the 2.4 GHz ISM band and supporting machine-to-machine (M2M) communication functions. Human-induced diffraction and multipath phenomena that affect RF signal propagation are leveraged for body localization while for fall detection a Hidden Markov Model is applied to discern different postures of the operator and to detect safety-relevant events by tracking the received signal strength indicator footprints. Fall detection performances are corroborated by extensive experimental measurements in different settings. In addition, we propose also a sensor fusion tool that is able to integrate the device-free RF-based sensing system within an industrial image sensors framework. Preliminary results, conducted during field trial measurements, confirm the effectiveness of the proposed approach in terms of localization accuracy, and sensitivity/specificity to correctly detect a fall event from pre-impact postures.

Modern robot manufacturing is fostering the implementation of hybrid production systems characterized by human–robot cooperative tasks. Safety technologies for workers protection require advanced sensing capabilities and flexible solutions that are able to monitor the movements of the operator in proximity of moving robots. This paper proposes the use of wireless device-free localization (DFL) methods and architectures to detect and track a human worker in a cooperative human–robot industrial workspace. The DFL system is composed of groups of massively interacting small, low-cost, embedded radio-frequency (RF) transceivers that perform received power measurements. These devices are anchored in fixed peripheral locations of the plant and provide the localization of the worker, who peculiarly carries neither wireless active devices (device-free) nor specific tracking sensors (sensor-free sensing). Operator motion is, in fact, estimated by tracking the perturbations of the radio field induced by the human body, considering the effect of concurrently moving robot as non-stationary interference. The proposed localization and detection algorithm is based on the jump linear Markovian system and the interactive multiple model method, and its positioning accuracy has been validated by experiments performed inside a robotic cell of an industrial test plant. The proposed DFL system has been implemented by employing IEEE 802.15.4 RF devices operating at 2.4 GHz and integrated into a software safety architecture. Finally, a software toolset has been designed to predict DFL accuracy, to verify experimental measurements, and also to support the integration with preinstalled industrial sensors to increase the accuracy of the augmented system.

Smart factories must speed up their processes to face new manufacturing challenges and, at the same time, demonstrate an extremely high degree of flexibility to reduce production costs and time. This kind of issues can be addressed by the cooperation between humans and robots in a mixed human-robot working environment. Robots have the compelling advantage of spatial precision and repeatability as well as the capability of applying defined forces. Humans, on the other hand, are especially skilled at complex manipulations and adapting to changing task requirements. In this complicate scenario of co-shared workplace and continuous human-robot interaction, safety strategies are a key requirement to avoid possible injuries to humans or fatal accidents. This chapter proposes a systemic approach to respond to these requirements. The approach merges and manages multiple sensing sources, redundant transmission protocols and software decision mechanisms, aiming to guarantee a continuous and reconfigurable co-share scenario that enables an operative interaction between human workers and robots in a controlled and safe environment. Furthermore, new technological solutions and innovative methodologies are presented for the definition of a safer workplace in human-robot interaction scenarios.

Nowadays industrial production is undergoing a continuous increase in flexibility requirements and production facilities have to cope with products diversities, high levels of uncertainties and frequent changes in production cycles. Robotic cells are an interesting solution for achieving the high level of flexibility essential for small batch production and customization, but they have to deal with an additional increase in complexity due to human interaction.

A multi-robot platform, made of a hybrid parallel kinematic machine and 2 KUKA LWR arms, is dedicated to open skull neuro-surgical tasks. Sub-millimeter accuracy is clearly required for both the absolute tool tracking and for good performances in motion compensation when the head is set free to move. An analysis of the sources of inaccuracies, mostly derived from the calibration phase, illustrates that errors are insufficiently reduced by stand-alone calibrations of the single robots. A method for volumetric compensation of errors is reported. A compensation transform is, in fact, computed during an offline training phase for a set of discretized subregions of the constrained head workspace. At runtime, a compensation motion is applied to robots so as to reach the desired real targets on anatomical parts. The resulting end-to-end static accuracy is distributed with median 0.75 mm and below 1 mm for the 95% of tests, with a 1:36 reduction factor from the starting conditions. The accuracy is evaluated also in dynamic tests with mild oscillatory patterns.

A case study of multi-robot platform calibration is reported in the domain of robot-assisted neurosurgery. The robot system is composed of a hybrid parallel kinematic machine and 2 KUKA LWR arms and is dedicated to awake surgery with head motion compensation. The target accuracy is sub-millimeter. Calibration errors are known to cumulate along the kinematic loops in the system, so a method of volumetric compensation of inaccuracies is applied. Configuration-dependent compensation homogeneous transforms populate a look-up table trained offline for a set of discrete subregions of the workspace. At runtime, the compensation is applied to the robot motion so to reach an end-to-end static accuracy distributed with a median 0.75 mm and below 1 mm for the 95% of tests, with a 1∶36 reduction factor from the default calibration conditions.

In the domain of human-robot cooperation for robot-assisted manufacturing, the worker protection is always imperative using both intrinsically-safe and standard industrial manipulators. Collaborative workspaces very often involve cluttered layouts and flexible workflows that may require frequent relocation of operators and the concurrent access to resources in close-quarter cooperation. With the objective of maximizing the productivity of workcells, preserving the safety of the cooperation, an optimization of safeguarded workspaces is introduced under the approach of ISO/TS 15066 Speed and Separation Monitoring (SSM) modality. A trajectory-dependent dynamic SSM is considered for establishing the minimum safety area, changing at runtime, in order to avoid overconservative restrictions in nonfunctional volumes. The effects of robot dynamics and distributed robot control are discussed and evaluated.

Safety in human-robot cooperation is a non-optional property of any modern robot manufacturing application. All actions and settings, in terms of hardware and software, are intended to prevent hazards. In the domain of workspace sharing, with Speed and Separation Monitoring (SSM) modes, some safety-critical components can rely on safety-rated localization of users and safe computation of kinematical entities. Common to sensing and algorithms, some core functions are likely to be distributed in a network of devices, not necessarily sharing a safety-rated fieldbus. On the computation side, floatingpoint algorithms are never performed in state-of-the-art applica-tions compliant with current regulation. The purpose of the paper is to discuss the use of unsafe devices and protocols for safety functions considering functional safety at system level. On top of that, realistic conditions in networking are directly affecting one of the principal parameters of safety, which is protection distances. Some experimental data are reported in the case of dynamic SSM, based on trajectory-dependent safeguarding volumes computed at runtime.