Toward a Framework for a Human-Robot Interaction

Sebastian Thrun

Human-Computer Interaction, No.19, 2004

Summary

                  The field of robotics has undergone a considerable change from the time it first appeared as a complete science, robots now perform many assembly and transportation tasks, often equipped with minimal sensing and computing, slaved to perform a repetitive task. The future is more and more seeing the introduction of service robots and this is mainly thanks to reduce in costs of many technologies required and increase in autonomy capabilities.

Robotics appears to be a broad discipline and therefore definitions of this science are not unique, a general definition has been done by the author in a previous paper (Thrun, 2002) a system of robotic sensors, actuators and algorithms. The United Nations has categorized robotics in three fields: industrial robotics, professional service robotics and personal service robotics.

Industrial robotics are the earliest commercial success; an industrial robot operates manipulating its physical environment, it is computer controlled and operates in industrial settings (for example on conveyor belts).

Industrial robotics started in the 60s with the first commercial manipulator, the Unimate, later on in the 70s Nissan Corporation automated an entire assembly line with robots, starting a real “robotic revolution”, simply it can be considered that today the ration human to worker to robots is approximately 10:1 (the automotive industry is definitely the one with biggest application of robotics). However industrial robots are not intended to operate directly with humans.

Professional service robots are the younger kind of robots and are projected to assist people, perhaps in accessible environments or in tasks where speed and precision won’t definitely be met by human operators (as it is becoming more common in surgery).

Personal service robots posses today the highest expected growth rate, they are projected to assist people in domestic tasks and for recreational activities, often these robots are humanoids.

In all three of these fields two are the main drivers: cost and safety, these appear to be the challenges of robotics.

Autonomy refers to the ability the robot has to accommodate variation in the environment, it is a very important factory in human-robot interaction. Industrial robots are not considered to be highly autonomous, they often are called for repetitive tasks and therefore can be programmed, a different scenario appears to be the on of service robots where complexity of the environment brings them to be design to be very autonomous since they have to be able to predict the environment uncertainties, to detect and accommodate people and so on.

Of course there is also a cost issue, which necessitates the personal robots to be low-cost, therefore it they are the most complicated since the need high levels of autonomy and low costs. In human robot interaction extremely important become the interface mechanism, industrial robots are often limited, in fact they hard programmed and programming language and simulation softwares appear to be intermediary between the robot and the human. Service robots of course require richer interfaces and therefore distinguished are indirect and direct interaction methods. Indirect interaction consists of a person operating a robot through a command, while direct interaction consist of a robot taking decision on its on in parallel with a human.

Different technologies exist in order to achieve different method of communication, an interesting example appears to be the Robonaus (Ambrose et al., 2001), a master-slave idea demonstrating how a robot can cooperate with astronaut on a space station. Speech synthetisers and screens also appear to be interesting direct interaction methods.

Investigating humanoids and appearance, together with social aspect of service robots are also important aspect which researched are today investigating for the future of robotics.

Key Concepts

Human Robot Interaction, Human Robot Cooperation

Tactile sensing for mechatronics – a state of art survey

M.H. Lee, H.R. Nicholls

Mechatronics, No. 9, 1999

Summary

                   In industrial applications, contact interaction are an important feature of physical manipulation systems, but research in the field of tactile sensors has undergone a drastic slowdown after the ’80, when is was supposed that it would had been a fundamental sensor for the following decades. A tactile sensor is therefore defined as a device that can measure a property of an object through the contact with it. The other 4 sensing modalities are basically all advanced today in technology and even computer vision has became cheaper.

The difficulties which have somehow stopped research in tactile sensors is due to the fact that in human being this sensing modality isn’t localized, it’s complicated to transduce and it’s difficult to imitate. In industry some basic forms of sensing, such as “spatial switches” are quite common and easily accessible, therefore they are not in the matter of this stat of art survey. In the 90’ the studies directed the transducing methods to the following technologies, not basically available: Resistance and Conductance, Capacitance, Piezoelectric and Pyroelectric, Magnetic, Magnetoelectric, Mechanical, Optical, Ultrasonic and strain gauges. Interesting researched have been performed in cutaneous sensor, which are basically divided in to extrinsic (mounted at or near the contact interface) and intrinsic sensing (which consist in derivation of contact data from force sensing within a mechanical structure), this study covers about the former one, which doesn’t deal with force/torque sensors. An important method for obtaining cutaneous sensor is by using array of integral sensing elements, which have been demonstrated to be capable of having a spatial resolution of 2-4 mm (Beebe). Gray and Fearing reported an 8 ⨯ 8 capacitive fabricated array of 1mm² area.

One of the major problems regard inverse analysis, which is the issue of computing the changes on the surface from the sensed data gathered remotely through the elastic medium, since there isn’t a unique solution.

Artificial sensing fingers appear to be another interesting application for exploration and grasping, in this field at least two types of tactile sensors are considered: one for contact point localization and one for detecting more spatially diffuse dynamic events, such as contact slip.

Soft materials are becoming an interest matter for tactile sensing research and gels, followed by powders appear to be the best material in terms of impact and strain energy dissipation, conformability to surface and hysteresis effects. Also the fact that human tissue is composed by electrolytic materials have inspired researched such as Sawahata, Gong and Osada to use polyacrylamide, which, with similar mechanical properties, can capture the electrical change (piezoelectric effect). Tactile sensor can also reduce kinematic errors in stiffness control by locating precise contact point and tracking changes, being useful for dexterous multi-fingered hands (Howe).

Whiskers have also objects under study, in fact they appear to be fast, accurate and cheap, essentially being single point sensors. Son, Cutkosky and Howe demonstrated how intrinsic and extrinsic tactile sensors can be effective with less than 1 mm error contact location. Tactile sensors appear to have application also in haptic perception (integration of cutaneous surface sensing with information from position and movement variable of the manipulator), teleoperation (remote human operating a robot) and virtual reality (for which multi-sensor gloves or other actuators have been creator to provide tactile sense to the operator). Processing of the data my be with fuzzy logic, rule-based systems or model-based systems, but neural networks appear to be the fastest.

Key Concepts

Tactile Sensors

Key Results

Toyota ins an example of organization pushing workers to have “safe partnership” with robots, in order to achieve this either intrinsically safer equipment must be provided (Tobita et al.) or there must be comprehensive collision avoidance (Suita et al.), therefore tactile sensors would be a fundamental tool for human robot interaction ensuring reliability and safety conditions.

Whose Job is it anyway? A Study of Human-Robot Interaction in a Collaborative Task

Pamela J. Hinds, Teresa L. Roberts, Hank Jones

Human-Computer Interaction, Volume 19, 2004

Summary

                  Human Robot cooperation is growing more and more and researches have supposed that humans may prefer working with human-like robots than machine-like, although, according to the authors, no test has been down up to the paper’s date (2004). The paper researches links with human likeness, status (subordinate, peer or supervisor) and dimensions. Today researches are divided mainly in two “team”, according to Brooks [2002], humanoids will have better communication chances than machine-like robots, while opponents believe that humanoid features may result in unrealistic expectations and in some cases even fear. In this research the case of underreliance is faced, being proved (Gawande, 2002) that people tend to resist technologies that are programmed to augment human decision making. Another aspect covered in this research is the level of responsibility that people assume for a certain task in certain conditions and with a certain robot cooperator.

The authors performed statistical test on 5 hypothesis: 1a) People rely on human-like robot partner more than a machine-like one; 1b) People will feel less responsible for the task when collaborating with a human like robot partner than a machine-like one; 2a) People will rely on the robot partner more when its characterized as a supervisor than when it is characterized as a subordinate; 2b) People will feel less responsible for a task when collaborating with a robot partner who is a supervisor than with a robot partner who is a subordinate or a peer; 3) People will feel the greatest amount of responsibility when collaborating with a machine-like robot subordinates as compared with machine-like robot subordinated. To test the tree hypothesis the researchers performed experiments to verify human likeness and status influence in human perception, the robot was operating in Wizard of Oz conditions (teleoperated) without the people performing been told.

The experiments have been performed with a the same robot, once wearing human-like features such as nose, ears, mouth and eyes been demonstrated (Di Salvo, Gemperle, Forlizzi and Kiesler, 2002) that there are the characteristics that most affect perception of human-likeness; the status has been previously communicated to the testers through written instruction (as been successfully done previously by Sande, 1986).

The experiment analyzed, through videotapes analysis, the attribution of credit and blame, specially using the concept of shared social identity analyzing the language used by the testers while working together with the robot.

Key Concepts

Human-Robot Cooperation, Team-working, Humanoids, Robot impact on humans

Key Results

The results have shown multiple aspects, first of all, not unexpected is the preference humans have in working with other humans rather than robots, but the difference regarding responsibility, attribution of blame and attribution of credit appears to be not statistically significant, as for the difference between human-like robot and machine-like robot. Hypothesis 1a and 1b appear therefore to be confirmed. It is interesting to notice how users tend communicated more with machine-like robots, since people perceive less common ground between themselves and the robot (Fussel & Krauss, 1992). Also it has been proved that people relied more on a peer robot than a subordinate or supervisor robot (when the robot is a supervisor then humans tend to blame the mistakes and attribute to themselves the success) and people feel much more responsible for the task when cooperating with a machine-like robot. This results suggests that the appearance of the robot is important according on the degree of responsibility required, when it’s needed to have more options then it would be better to have a machine-like robot (Robert et al., 1994), in the case of high hazardous environment and risk then humanoids may be a good choice so that people may delegate easily responsibilities to them.

Safety Issues for Human-Robot Copperation in Manufacturing Systems

Agostino De Santis, Bruno Siciliano

Tools and Perspectives in Virtual Manufacturing, July 10^th 2008 – July 11^th 2008

Summary

                  The next generation robots will be enhanced with the challenging and revolutionary feature of physical Human Robot Interaction (pHRI), making safety and dependability key concepts of the future of robotics.

Safety, being fundamental for future HRI, appears to cover several aspect, such as: mechanics, electronics and software. Up to now safety has force robots to be segregated from the operators working environment, cHRI (cognitive Human Robot Interaction) has been commonly debated in the scientific community, however robots are distinct from computers and other machines: they generate force and have “body”, making it be an intelligent connection in the direction of pHRI, allowing more and more safe, fast and accurate motions without third-party sensors.

The new robots are then considered under two criteria: safety (which includes also “mental safety”, which is the awareness of robot motion) and dependability (which allows “human-in-the-loop” conditions). Standards at the moment are not yet ready for the share of operational space, work is being going on the international ISO 10218 in order to include aspect on robot’s work place.

It is clear that in order to allow humans and robots to share common working environment, metrics regarding safety levels must be introduce and not surprisingly measures already use in the automotive sector are currently used. Two methods are applied: direct interaction (for head collision with another solid object) and indirect interaction (for sudden head motion with no direct contact). The scaling used (AIS – Abbreviated Injury Scale) is indicating the injury severity on the overall injury (MAIS); injury types are then divided in a classification related to type and consequences and is based on an ascending scale from 0 to 6. Paradoxically the result from this metric is that it enourages the usa of robots, since it is considered that even withouth the use of robots operator get injured. Safety can be taken with two different approaches: intrinsic safety and actuation (for example a distribuition macromini actuation DM² [Zinn,2002], where for each d.o.f. a pair of actuators connected in parallel and located in different parts on the manipulator, ensuring lower inertia and good performance; VIA – Variable Impendance Approach, is a mechanical control co-design that allows varying stiffness, damping and gear-ratio in order to minimize the negative effects of control performance) and safety by mean of control (which could be either position controlled or force/impendance control, the latter being direct in the case of a feedback loop control or indirect with a motion control loop). In the case of safety by mean of control, we my consider reactive control obtained through potential fields, which have the mission of creating attracting or repelling volumes, an example is the skeleton algorithm, which creates rotational volumes in proximity of links, this created a virtual region which approaches the real volume of a considered part of a manipulator.

The algorithm allows to use the human head avoidance illustrated previously and in case of a safe robot, the additional safety can be considered to be enough.

The issues which the authors encounted are regarding communication, in fact a emergency stop of the robot still has to be tested in case of particular necessities, but still it appears to be a fast modelling method.

The importance of simulation useing virtual reality is underlined, since it provides and ergonomic evaluation, comfort measure and of course a simulation of possible and eventual malfuctioning, allowing a fast comparison of interface, appearance and kinematic parameters.

Key Concepts

Safety, Virtual Reality, Simulation, Reactive Control, skeleton algorithm, physical Human Robot Interaction.