Improving human robot collaboration through Force/Torque based learning for object manipulation

Human–Robot Collaboration (HRC) is a term used to describe tasks in which robots and humans work together to achieve a goal. Unlike traditional industrial robots, collaborative robots need to be adaptive; able to alter their approach to better suit the situation and the needs of the human partner. As traditional programming techniques can struggle with the complexity required, an emerging approach is to learn a skill by observing human demonstration and imitating the motions; commonly known as Learning from Demonstration (LfD). In this work, we present a LfD methodology that combines an ensemble machine learning algorithm (i.e. Random Forest (RF)) with stochastic regression, using haptic information captured from human demonstration. The capabilities of the proposed method are evaluated using two collaborative tasks; co-manipulation of an object (where the human provides the guidance but the robot handles the objects weight) and collaborative assembly of simple interlocking parts. The proposed method is shown to be capable of imitation learning; interpreting human actions and producing equivalent robot motion across a diverse range of initial and final conditions. After verifying that ensemble machine learning can be utilised for real robotics problems, we propose a further extension utilising Weighted Random Forest (WRF) that attaches weights to each tree based on its performance. It is then shown that the WRF approach outperforms RF in HRC tasks.     

Safe and intuitive manual guidance of a robot manipulator using adaptive admittance control towards robot agility

Key areas of robot agility include methods that increase capability and flexibility of industrial robots and facilitate robot re-tasking. Manual guidance can achieve robot agility effectively, provided that a safe and smooth interaction is guaranteed when the user exerts an external force on the end effector. We approach this by designing an adaptive admittance law that can adjust its parameters to modify the robot compliance in critical areas of the workspace, such as near and on configuration singularities, joint limits, and workspace limits, for a smooth and safe operation. Experimental validation was done with two tests: a constraint activation test and a 3D shape tracing task. In the first one, we validate the proper response to constraints and in the second one, we compare the proposed approach with different admittance parameter tuning strategies using a drawing task where the user is asked to guide the robot to trace a 3D profile with an accuracy or speed directive and evaluate performance considering path length error and execution time as metrics, and a questionnaire for user perception. Results show that appropriate response to individual and simultaneous activation of the aforementioned constraints for a safe and intuitive manual guidance interaction is achieved and that the proposed parameter tuning strategy has better performance in terms of accuracy, execution time, and subjective evaluation of users.     

Infants' sensitivity to optical flow for controlling posture.

Infants' sensitivity to optical flow for controlling sitting and standing was tested using a "moving room" in which all of the walls moved together, or only the side walls or front wall moved. Two questions motivated this research. (a) is the optical flow necessary for inducing postural compensations spatially distributed in the optic array? (b) Do visually induced compensations follow a developmental progression, or alternatively, emerge all at once? Experiment 1 was designed to test postural compensations by 14-month-old infants capable of standing in the moving room. Experiment 2 was designed to test postural compensations by 5- to 9-month-old infants who were passively supported while sitting in the moving room. The results revealed that partial flow is generally sufficient for inducing postural compensations, but that the amplitude and consistency of the response depend on the location of the flow in the optic array. In addition, there was evidence suggesting that compensatory responses become increasingly systematic during the second half of the first year. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Editorial: January 1992.

Explains changes in the American Psychologist (AP) and reveals plans for 3 special issues in 1992 and 1993 (including a commemorative issue to observe the American Psychological Association's (APA's) centennial year. AP's standard editorial procedure, reasons for some rejections, and reconsideration of submissions are discussed. The editor notes that APA's new building (already a financial success) and its highly successful publications program can become an additional source of income to APA. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The Synthesis of Covalent Triazine-Based Frameworks via Friedel–Crafts Reactions of Cyanuric Chloride with Thienyl and Carbazolyl Derivatives for Fluorescence Sensing to Picric Acid,Iodine and Capturing Iodine

A multifunctional thiophene-based covalent triazine framework (TTPATTh) with triphenylamine as core is synthesized by Friedel–Crafts reaction of cyanuric chloride with thienyl derivative for the first time. The yield of TTPATTh (99.59%) is far higher than that of the carbazole-based CTF (TTPATCz, 47.03%). TTPATTh and TTPATCz possess high BET surface areas with 1235 and 2501 m² g^–1 as well as high pore volumes with 1.60 and 2.23 cm³ g^–1, respectively. TTPATTh and TTPATCz have high thermal stability with high thermal decomposition temperatures of 514 and 598 °C in nitrogen atmosphere. With the introduction of triazine rings, the fluorescence sensing sensitivities of TTPATTh and TTPATCz to picric acid and iodine are improved significantly. Especially for TTPATTh, the K_sv values reach 5.95 × 10⁵ and 1.61 × 10⁴ L mol^–1, and LODs reach 1.02 × 10^–12 and 1.86 × 10^–12 mol L^–1. To the best of the knowledge, this is the most sensitive value among thiophene-based porous organic polymers to PA and I₂. Furthermore, TTPATTh and TTPATCz can also adsorb iodine in vapor phase, cyclohexane solution and aqueous solution, and release iodine by heating or in ethanol solution. The efficiency of controlling the release of iodine is higher than that in ethanol.     

Catalytic feasibility of Ce-doped LaCoO3 systems for chlorobenzene oxidation: An analysis of synthesis method

A family of Ce-doped LaCoO₃ perovskites are presented as possible catalysts for Cl–VOCs elimination. These materials with different contents of Ce were obtained through the citrate and the reactive grinding methods. The insertion of Ce in the original perovskite structure favours the presence of Co²⁺/Co³⁺ and Ce³⁺/Ce⁴⁺ redox pairs and a higher content of oxygen vacancies that enhances the catalytic performance in chlorobenzene combustion based on differential kinetics studies. The family obtained by the grinding method presents a performance as high as that synthesized by citrate method. Thus, the reactive grinding is a feasible green chemistry alternative to obtain a catalyst with the same performance as that obtained from traditional methods. Finally, the stability of samples was evaluated under total combustion reaction conditions showing an excellent activity during 45 h time on stream.     

Asynchronous decentralized event-triggered control

In this paper we propose an approach to the implementation of controllers with decentralized strategies triggering controller updates. We consider set-ups with a central node in charge of the computation of the control commands, and a set of not co-located sensors providing measurements to the controller node. The solution we propose does not require measurements from the sensors to be synchronized in time. The sensors in our proposal provide measurements in an aperiodic way triggered by local conditions. Furthermore, in the proposed implementation (most of) the communication between nodes requires only the exchange of one bit of information (per controller update), which could aid in reducing transmission delays and as a secondary effect result in fewer transmissions being triggered.     

Utility of stereoscopic displays for indirect-vision driving and robot teleoperation

The effectiveness of an active shutter-glasses stereoscopic display (SD) and a passive polarised SD was evaluated in a live robot-teleoperation task and a simulated indirect-vision driving task in various terrains. Overall, participants completed their tasks significantly faster with the SDs in three-dimensional (3D) mode than with the SDs in the baseline 2D mode. They also navigated more accurately with the SDs in 3D mode. When the effectiveness of the two types of SDs was examined separately, results showed that the active shutter-glasses SD resulted in faster responses and task completion times than the passive polarised SD, though most of the differences failed to reach statistical significance. Perceived workload when interacting with the two SD systems did not differ significantly between the active versus passive display types or between the 3D and 2D modes of operation; however, participants reported more severe discomfort after interacting with the passive polarised SD.     

A 3D analysis of the joint torques developed during driver's ingress–egress motion

Providing an easy ingress–egress (I/E) movement remains a challenge for car designers. I/E has been largely studied in kinematics, but not in dynamics. This study proposes: (1) to evaluate and describe the motor torques developed in the lower limbs and lumbar joints during I/E motions and (2) to analyse the influence of the car geometry and subject anthropometry. An experiment was performed to observe 15 subjects of three anthropometrical groups getting in and out of a car mock-up simulating three different vehicle configurations. Motor torques were extracted using an inverse dynamics analysis. Both ingress and egress motions were primarily characterised by large torques. Overall, the taller a subject and the lower the seat of the vehicle were, the larger the peak torques were. Moreover, peak torques were higher for egress than ingress. These results are discussed in regard to the current knowledge on I/E ergonomics.     

Validation of a task demand measure for predicting mental workloads of physical therapists

The purpose of this study is to validate an analytical method in assessing demanded mental workloads for physical therapists, and to discuss its possible ergonomics implications on the design of healthcare working systems in which physical therapists are considered as the users. A task analysis was first used to understand the operation steps of three identified physical therapies. Then, the McCracken–Aldrich technique was applied to assign ratings of mental workload demanded for performing each step of the therapies. Finally, the assigned ratings were validated by the analysis of correlation with the answers of the NASA-TLX questionnaire collected from seventeen physical therapists in the rehabilitation center of a university-affiliated hospital. Results showed that the proposed McCracken–Aldrich technique was suitable as an analysis tool for predicting metal workloads of physical therapists. Some possible implications about the information provision and user interface design for reducing therapists' mental workloads on current therapy operations were discussed.Relevance to industryResults of this paper are expected to contribute the research and development in healthcare industry on its system design and workflow analysis.