Nathan Kirchner

Nonverbal robot-group interaction using an imitated gaze cue

Ensuring that a particular and unsuspecting member of a group is the recipient of a salient-item hand-over is a complicated interaction. The robot must effectively, expediently and reliably communicate its intentions to advert any tendency within the group towards antinormative behaviour. In this paper, we study how a robot can establish the participant roles of such an interaction using imitated social and contextual cues. We designed two gaze cues, the first was designed to discourage antinormative behaviour through individualising a particular member of the group and the other to the contrary. We designed and conducted a field experiment (456 participants in 64 trials) in which small groups of people (between 3 and 20 people) assembled in front of the robot, which then attempted to pass a salient object to a particular group member by presenting a physical cue, followed by one of two variations of a gaze cue. Our results showed that presenting the individualising cue had a significant (z=3.733, p=0.0002 ) effect on the robots ability to ensure that an arbitrary group member did not take the salient object and that the selected participant did.

Head-to-shoulder signature for person recognition

Ensuring that an interaction is initiated with a particular and unsuspecting member of a group is a complex task. As a first step the robot must effectively, expediently and reliably recognise the humans as they carry on with their typical behaviours (in situ). A method for constructing a scale and viewing angle robust feature vector (from analysing a 3D pointcloud) designed to encapsulate the inter-person variations in the size and shape of the peoples head to shoulder region (Head-to-shoulder signature - HSS) is presented. Furthermore, a method for utilising said feature vector as the basis of person recognition via a Support-Vector Machine is detailed. An empirical study was performed in which person recognition was attempted on in situ data collected from 25 participants over 5 days in a office environment. The results report a mean accuracy over the 5 days of 78.15% and a peak accuracy 100% for 9 participants. Further, the results show a considerably better-than-random (1/23 = 4.5%) result for when the participants were: in motion and unaware they were being scanned (52.11%), in motion and face directly away from the sensor (36.04%), and post variations in their general appearance. Finally, the results show the HSS has considerable ability to accommodate for a persons head, shoulder and body rotation relative to the sensor - even in cases where the person is faced directly away from the robot.

An Algorithm for Surface Growing from Laser Scan Generated Point Clouds

In robot applications requiring interaction with a partially/unknown environment, mapping is of paramount importance. This paper presents an effective surface growing algorithm for map building based on laser scan generated point clouds. The algorithm directly converts a point cloud into a surface and normals form which sees a significant reduction in data size and is in a desirable format for planning the interaction with surfaces. It can be used in applications such as robotic cleaning, painting and welding.

Bootstrapping navigation and path planning using human positional traces

Navigating and path planning in environments with limited a priori knowledge is a fundamental challenge for mobile robots. Robots operating in human-occupied environments must also respect sociocontextual boundaries such as personal workspaces. There is a need for robots to be able to navigate in such environments without having to explore and build an intricate representation of the world. In this paper, a method for supplementing directly observed environmental information with indirect observations of occupied space is presented. The proposed approach enables the online inclusion of novel human positional traces and environment information into a probabilistic framework for path planning. Encapsulation of sociocontextual information, such as identifying areas that people tend to use to move through the environment, is inherently achieved without supervised learning or labelling. Our method bootstraps navigation with indirectly observed sensor data, and leverages the flexibility of the Gaussian process (GP) for producing a navigational map that sampling based path planers such as Probabilistic Roadmaps (PRM) can effectively utilise. Empirical results on a mobile platform demonstrate that a robot can efficiently and socially-appropriately reach a desired goal by exploiting the navigational map in our Bayesian statistical framework.

Surface Type Classification With a Laser Range Finder

This paper presents a system for surface classification using a laser range finder. It is shown that the return intensities and range errors provide sufficient information to distinguish a wide range of surfaces commonly found in a number of environments. A supervised learning scheme (using curves representing the return intensity and range error as a function of angle of incidence) is used to classify the surface type of planar patches. Extensive experimental evidence is presented to demonstrate the potential of the proposed technique. The surface type classification, which uses a typical laser range finder, is targeted for use with autonomous robotic systems in which significantly different interaction is required for each of the various materials present. Results from an on-site experiment demonstrate that the information from the laser range finder is sufficient to identify the different materials (via their surface properties) present in a scene where a bridge structure is being prepared for grit blasting.

Safe and Efficient Autonomous Exploration Technique for 3D Mapping of a Complex Bridge Maintenance Environment

This paper describes a technique for autonomously exploring a complex steel bridge environment using a 6DOF anthropomorphic robotic arm, instrumented with a laser range scanner. Potential knowledge gained from a 3D range scan at an end-effector position and orientation (pose) is estimated, then arm configurations which avoid obstacles and unknown areas are computed using an optimisation approach. Safe pose solutions are compared in terms of potential gain of new weighted-information and minimal joint movement. Both simulations and robotic platform results show exploration of unknown areas occurs in a consistent and timely manner - taking an average of 4.5secs to calculate the next safe valid robot arm poses. Complex environments, typical in bridge maintenance, can be explored using an anthropomorphic arm equipped with this technique.

A robot centric perspective on the HRI paradigm

The industrial revolution undoubtedly defined the role of machines in our society, and it directly shaped the paradigm for human machine interaction - a paradigm which was inherited by the field of Human Robot Interaction (HRI) as the machines became robots. This paper argues that, for a foreseeable set of interactions, reshaping this paradigm would result in more effective and more often successful interactions. This paper presents our Robot Centric paradigm for HRI. Evidence in the form of summaries of relevant literature and our past efforts in developing social-robotics enabling technology is presented to support our paradigm. A definition and a set of recommendations for designing the key enabling component, sociocontextual cues, of our paradigm are presented. Finally, empirical evidence generated through a number of experiments and field studies (N = 456 and N = 320) demonstrates our paradigm is both feasibly incorporated into HRI and moreover, yields significant contributions to the successfulness of a set of HRIs.

Moderating a Robot's Ability to Influence People Through its Level of Sociocontextual Interactivity

A range of situations exist in which it would be useful to influence people’s behavior in public spaces, for example to improve the efficiency of passenger flow in congested train stations. We have identified our previously developed Robot Centric paradigm of Human-RobotInteraction (HRI), which positions robots as interaction peers, as a potentially suitable model to achieve more effective influence through defining and exploiting the interactivity of robots (that is, their ability to moderate their issued sociocontextual cues based on the behavioral information read from humans). In this paper, we investigate whether increasing a robot’s interactivity will increase the effectiveness of its influence on people in public spaces. A two-part study (total

Listening for people: Exploiting the spectral structure of speech to robustly perceive the presence of people

n = { 273)}

An effort-based evaluation of pedestrian route choice

was conducted in both a major Australian public train station