Frontiers in Robotics and AI

RSS Feed for Frontiers in Robotics and AI | New and Recent Articles
Subscribe to Frontiers in Robotics and AI feed

Participatory design (PD) has been used to good success in human-robot interaction (HRI) but typically remains limited to the early phases of development, with subsequent robot behaviours then being hardcoded by engineers or utilised in Wizard-of-Oz (WoZ) systems that rarely achieve autonomy. In this article, we present LEADOR (Led-by-Experts Automation and Design Of Robots), an end-to-end PD methodology for domain expert co-design, automation, and evaluation of social robot behaviour. This method starts with typical PD, working with the domain expert(s) to co-design the interaction specifications and state and action space of the robot. It then replaces the traditional offline programming or WoZ phase by an in situ and online teaching phase where the domain expert can live-program or teach the robot how to behave whilst being embedded in the interaction context. We point out that this live teaching phase can be best achieved by adding a learning component to a WoZ setup, which captures implicit knowledge of experts, as they intuitively respond to the dynamics of the situation. The robot then progressively learns an appropriate, expert-approved policy, ultimately leading to full autonomy, even in sensitive and/or ill-defined environments. However, LEADOR is agnostic to the exact technical approach used to facilitate this learning process. The extensive inclusion of the domain expert(s) in robot design represents established responsible innovation practice, lending credibility to the system both during the teaching phase and when operating autonomously. The combination of this expert inclusion with the focus on in situ development also means that LEADOR supports a mutual shaping approach to social robotics. We draw on two previously published, foundational works from which this (generalisable) methodology has been derived to demonstrate the feasibility and worth of this approach, provide concrete examples in its application, and identify limitations and opportunities when applying this framework in new environments.

In recent years, the demand for remote services has increased with concerns regarding the spread of infectious diseases and employees’ quality of life. Many attempts have been made to enable store staff to provide various services remotely via avatars displayed to on-site customers. However, the workload required on the part of service staff by the emerging new work style of operating avatar robots remains a concern. No study has compared the performance and perceived workload of the same staff working locally versus remotely via an avatar. In this study, we conducted an experiment to identify differences between the performance of in-person services and remote work through an avatar robot in an actual public space. The results showed that there were significant differences in the partial performance between working via an avatar and working locally, and we could not find significant difference in the overall performance. On the other hand, the perceived workload was significantly lower when the avatar robot was used. We also found that customers reacted differently to the robots and to the in-person participants. In addition, the workload perceived by operators in the robotic task was correlated with their personality and experience. To the best of our knowledge, this study is the first investigation of both performance and workload in remote customer service through robotic avatars, and it has important implications for the implementation of avatar robots in service settings.

In the inspection work involving foodstuffs in food factories, there are cases where people not only visually inspect foodstuffs, but must also physically touch foodstuffs with their hands to find foreign or undesirable objects mixed in the product. To contribute to the automation of the inspection process, this paper proposes a method for detecting foreign objects in food based on differences in hardness using a camera-based tactile image sensor. Because the foreign objects to be detected are often small, the tactile sensor requires a high spatial resolution. In addition, inspection work in food factories requires a sufficient inspection speed. The proposed cylindrical tactile image sensor meets these requirements because it can efficiently acquire high-resolution tactile images with a camera mounted inside while rolling the cylindrical sensor surface over the target object. By analyzing the images obtained from the tactile image sensor, we detected the presence of foreign objects and their locations. By using a reflective membrane-type sensor surface with high sensitivity, small and hard foreign bodies of sub-millimeter size mixed in with soft food were successfully detected. The effectiveness of the proposed method was confirmed through experiments to detect shell fragments left on the surface of raw shrimp and bones left in fish fillets.

In recent years, the governance of robotic technologies has become an important topic in policy-making contexts. The many potential applications and roles of robots in combination with steady advances in their uptake within society are expected to cause various unprecedented issues, which in many cases will increase the demand for new policy measures. One of the major issues is the way in which societies will address potential changes in the moral and legal status of autonomous social robots. Robot standing is an important concept that aims to understand and elaborate on such changes in robots’ status. This paper explores the concept of robot standing as a useful idea that can assist in the anticipatory governance of social robots. However, at the same time, the concept necessarily involves forms of speculative thinking, as it is anticipating a future that has not yet fully arrived. This paper elaborates on how such speculative engagement with the potential of technology represents an important point of discussion in the critical study of technology more generally. The paper then situates social robotics in the context of anticipatory technology governance by emphasizing the idea that robots are currently in the process of becoming constituted as objects of governance. Subsequently, it explains how specifically a speculative concept like robot standing can be of value in this process.

Approaches to robotic manufacturing, assembly, and servicing of in-space assets range from autonomous operation to direct teleoperation, with many forms of semi-autonomous teleoperation in between. Because most approaches require one or more human operators at some level, it is important to explore the control and visualization interfaces available to those operators, taking into account the challenges due to significant telemetry time delay. We consider one motivating application of remote teleoperation, which is ground-based control of a robot on-orbit for satellite servicing. This paper presents a model-based architecture that: 1) improves visualization and situation awareness, 2) enables more effective human/robot interaction and control, and 3) detects task failures based on anomalous sensor feedback. We illustrate elements of the architecture by drawing on 10 years of our research in this area. The paper further reports the results of several multi-user experiments to evaluate the model-based architecture, on ground-based test platforms, for satellite servicing tasks subject to round-trip communication latencies of several seconds. The most significant performance gains were obtained by enhancing the operators’ situation awareness via improved visualization and by enabling them to precisely specify intended motion. In contrast, changes to the control interface, including model-mediated control or an immersive 3D environment, often reduced the reported task load but did not significantly improve task performance. Considering the challenges of fully autonomous intervention, we expect that some form of teleoperation will continue to be necessary for robotic in-situ servicing, assembly, and manufacturing tasks for the foreseeable future. We propose that effective teleoperation can be enabled by modeling the remote environment, providing operators with a fused view of the real environment and virtual model, and incorporating interfaces and control strategies that enable interactive planning, precise operation, and prompt detection of errors.

A frequent concern for robot manipulators deployed in dangerous and hazardous environments for humans is the reliability of task executions in the event of a joint failure. A redundant robotic manipulator can be used to mitigate the risk and guarantee a post-failure task completion, which is critical for instance for space applications. This paper describes methods to analyze potential risks due to a joint failure, and introduces tools for fault-tolerant task design and path planning for robotic manipulators. The presented methods are based on off-line precomputed workspace models. The methods are general enough to cope with robots with any type of joint (revolute or prismatic) and any number of degrees of freedom, and might include arbitrarily shaped obstacles in the process, without resorting to simplified models. Application examples illustrate the potential of the approach.

Creativity, in one sense, can be seen as an effort or action to bring novelty. Following this, we explore how a robot can be creative by bringing novelty in a human–robot interaction (HRI) scenario. Studies suggest that proactivity is closely linked with creativity. Proactivity can be defined as acting or interacting by anticipating future needs or actions. This study aims to explore the effect of proactive behavior and the relation of such behaviors to the two aspects of creativity: 1) the perceived creativity observed by the user in the robot’s proactive behavior and 2) creativity of the user by assessing how creativity in HRI can be shaped or influenced by proactivity. We do so by conducting an experimental study, where the robot tries to support the user on the completion of the task regardless of the end result being novel or not and does so by exhibiting anticipatory proactive behaviors. In our study, the robot instantiates a set of verbal communications as proactive robot behavior. To our knowledge, the study is among the first to establish and investigate the relationship between creativity and proactivity in the HRI context, based on user studies. The initial results have indicated a relationship between observed proactivity, creativity, and task achievement. It also provides valuable pointers for further investigation in this domain.

During communication, humans express their emotional states using various modalities (e.g., facial expressions and gestures), and they estimate the emotional states of others by paying attention to multimodal signals. To ensure that a communication robot with limited resources can pay attention to such multimodal signals, the main challenge involves selecting the most effective modalities among those expressed. In this study, we propose an active perception method that involves selecting the most informative modalities using a criterion based on energy minimization. This energy-based model can learn the probability of the network state using energy values, whereby a lower energy value represents a higher probability of the state. A multimodal deep belief network, which is an energy-based model, was employed to represent the relationships between the emotional states and multimodal sensory signals. Compared to other active perception methods, the proposed approach demonstrated improved accuracy using limited information in several contexts associated with affective human–robot interaction. We present the differences and advantages of our method compared to other methods through mathematical formulations using, for example, information gain as a criterion. Further, we evaluate performance of our method, as pertains to active inference, which is based on the free energy principle. Consequently, we establish that our method demonstrated superior performance in tasks associated with mutually correlated multimodal information.

To what extent, if any, should the law protect sentient artificial intelligence (that is, AI that can feel pleasure or pain)? Here we surveyed United States adults (n = 1,061) on their views regarding granting 1) general legal protection, 2) legal personhood, and 3) standing to bring forth a lawsuit, with respect to sentient AI and eight other groups: humans in the jurisdiction, humans outside the jurisdiction, corporations, unions, non-human animals, the environment, humans living in the near future, and humans living in the far future. Roughly one-third of participants endorsed granting personhood and standing to sentient AI (assuming its existence) in at least some cases, the lowest of any group surveyed on, and rated the desired level of protection for sentient AI as lower than all groups other than corporations. We further investigated and observed political differences in responses; liberals were more likely to endorse legal protection and personhood for sentient AI than conservatives. Taken together, these results suggest that laypeople are not by-and-large in favor of granting legal protection to AI, and that the ordinary conception of legal status, similar to codified legal doctrine, is not based on a mere capacity to feel pleasure and pain. At the same time, the observed political differences suggest that previous literature regarding political differences in empathy and moral circle expansion apply to artificially intelligent systems and extend partially, though not entirely, to legal consideration, as well.

Plants have evolved different mechanisms to disperse from parent plants and improve germination to sustain their survival. The study of seed dispersal mechanisms, with the related structural and functional characteristics, is an active research topic for ecology, plant diversity, climate change, as well as for its relevance for material science and engineering. The natural mechanisms of seed dispersal show a rich source of robust, highly adaptive, mass and energy efficient mechanisms for optimized passive flying, landing, crawling and drilling. The secret of seeds mobility is embodied in the structural features and anatomical characteristics of their tissues, which are designed to be selectively responsive to changes in the environmental conditions, and which make seeds one of the most fascinating examples of morphological computation in Nature. Particularly clever for their spatial mobility performance, are those seeds that use their morphology and structural characteristics to be carried by the wind and dispersed over great distances (i.e. “winged” and “parachute” seeds), and seeds able to move and penetrate in soil with a self-burial mechanism driven by their hygromorphic properties and morphological features. By looking at their motion mechanisms, new design principles can be extracted and used as inspiration for smart artificial systems endowed with embodied intelligence. This mini-review systematically collects, for the first time together, the morphological, structural, biomechanical and aerodynamic information from selected plant seeds relevant to take inspiration for engineering design of soft robots, and discusses potential future developments in the field across material science, plant biology, robotics and embodied intelligence.

Robots for minimally invasive surgery introduce many advantages, but still require the surgeon to alternatively control the surgical instruments and the endoscope. This work aims at providing autonomous navigation of the endoscope during a surgical procedure. The autonomous endoscope motion was based on kinematic tracking of the surgical instruments and integrated with the da Vinci Research Kit. A preclinical usability study was conducted by 10 urologists. They carried out an ex vivo orthotopic neobladder reconstruction twice, using both traditional and autonomous endoscope control. The usability of the system was tested by asking participants to fill standard system usability scales. Moreover, the effectiveness of the method was assessed by analyzing the total procedure time and the time spent with the instruments out of the field of view. The average system usability score overcame the threshold usually identified as the limit to assess good usability (average score = 73.25 > 68). The average total procedure time with the autonomous endoscope navigation was comparable with the classic control (p = 0.85 > 0.05), yet it significantly reduced the time out of the field of view (p = 0.022 < 0.05). Based on our findings, the autonomous endoscope improves the usability of the surgical system, and it has the potential to be an additional and customizable tool for the surgeon that can always take control of the endoscope or leave it to move autonomously.

Dielectric elastomer actuators (DEAs) are a promising actuator technology for soft robotics. As a configuration of this technology, stacked DEAs afford a muscle-like contraction that is useful to build soft robotic systems. In stacked DEAs, dielectric and electrode layers are alternately stacked. Thus, often a dedicated setup with complicated processes or sometimes laborious manual stacking of the layers is required to fabricate stacked actuators. In this study, we propose a method to monolithically fabricate stacked DEAs without alternately stacking the dielectric and electrode layers. In this method, the actuators are fabricated mainly through two steps: 1) molding of an elastomeric matrix containing free-form microfluidic channels and 2) injection of a liquid conductive material that acts as an electrode. The feasibility of our method is investigated via the fabrication and characterization of simple monolithic DEAs with multiple electrodes (2, 4, and 10). The fabricated actuators are characterized in terms of actuation stroke, output force, and frequency response. In the actuators, polydimethylsiloxane (PDMS) and eutectic gallium–indium (EGaIn) are used for the elastomeric matrix and electrode material, respectively. Microfluidic channels are realized by dissolving a three-dimensional printed part suspended in the elastomeric structure. The experimental results show the successful implementation of the proposed method and the good agreement between the measured data and theoretical predication, validating the feasibility of the proposed method.

Stationary motorized cycling assisted by functional electrical stimulation (FES) is a popular therapy for people with movement impairments. Maximizing volitional contributions from the rider of the cycle can lead to long-term benefits like increased muscular strength and cardiovascular endurance. This paper develops a combined motor and FES control system that tasks the rider with maintaining their cadence near a target point using their own volition, while assistance or resistance is applied gradually as their cadence approaches the lower or upper boundary, respectively, of a user-defined safe range. Safety-ensuring barrier functions are used to guarantee that the rider’s cadence is constrained to the safe range, while minimal assistance is provided within the range to maximize effort by the rider. FES stimulation is applied before electric motor assistance to further increase power output from the rider. To account for uncertain dynamics, barrier function methods are combined with robust control tools from Lyapunov theory to develop controllers that guarantee safety in the worst-case. Because of the intermittent nature of FES stimulation, the closed-loop system is modeled as a hybrid system to certify that the set of states for which the cadence is in the safe range is asymptotically stable. The performance of the developed control method is demonstrated experimentally on five participants. The barrier function controller constrained the riders’ cadence in a range of 50 ± 5 RPM with an average cadence standard deviation of 1.4 RPM for a protocol where cadence with minimal variance was prioritized and used minimal assistance from the motor (4.1% of trial duration) in a separate protocol where power output from the rider was prioritized.

This article discusses the creative and technical approaches in a performative robot project called “Embodied Musicking Robots” (2018–present). The core approach of this project is human-centered AI (HC-AI) which focuses on the design, development, and deployment of intelligent systems that cooperate with humans in real time in a “deep and meaningful way.”1 This project applies this goal as a central philosophy from which the concepts of creative AI and experiential learning are developed. At the center of this discussion is the articulation of a shift in thinking of what constitutes creative AI and new HC-AI forms of computational learning from inside the flow of the shared experience between robots and humans. The central case study (EMRv1) investigates the technical solutions and artistic potential of AI-driven robots co-creating with an improvising human musician (the author) in real time. This project is ongoing, currently at v4, with limited conclusions; other than this, the approach can be felt to be cooperative but requires further investigation.

Biodegradability is an important property for soft robots that makes them environmentally friendly. Many biodegradable materials have natural origins, and creating robots using these materials ensures sustainability. Hence, researchers have fabricated biodegradable soft actuators of various materials. During microbial degradation, the mechanical properties of biodegradable materials change; these cause changes in the behaviors of the actuators depending on the progression of degradation, where the outputs do not always remain the same against identical inputs. Therefore, to achieve appropriate operation with biodegradable soft actuators and robots, it is necessary to reflect the changes in the material properties in their design and control. However, there is a lack of insight on how biodegradable actuators change their actuation characteristics and how to identify them. In this study, we build and validate a framework that clarifies changes in the mechanical properties of biodegradable materials; further, it allows prediction of the actuation characteristics of degraded soft actuators through simulations incorporating the properties of the materials as functions of the degradation rates. As a biodegradable material, we use a mixture of gelatin and glycerol, which is fabricated in the form of a pneumatic soft actuator. The experimental results show that the actuation performance of the physical actuator reduces with the progression of biodegradation. The experimental data and simulations are in good agreement (R2 value up to 0.997), thus illustrating the applicability of our framework for designing and controlling biodegradable soft actuators and robots.

It is almost a foregone conclusion that robots cannot be morally responsible agents, both because they lack traditional features of moral agency like consciousness, intentionality, or empathy and because of the apparent senselessness of holding them accountable. Moreover, although some theorists include them in the moral community as moral patients, on the Strawsonian picture of moral community as requiring moral responsibility, robots are typically excluded from membership. By looking closely at our actual moral responsibility practices, however, I determine that the agency reflected and cultivated by them is limited to the kind of moral agency of which some robots are capable, not the philosophically demanding sort behind the traditional view. Hence, moral rule-abiding robots (if feasible) can be sufficiently morally responsible and thus moral community members, despite certain deficits. Alternative accountability structures could address these deficits, which I argue ought to be in place for those existing moral community members who share these deficits.

Background: Play is critical for children’s physical, cognitive, and social development. Technology-based toys like robots are especially of interest to children. This pilot study explores the affordances of the play area provided by developmentally appropriate toys and a mobile socially assistive robot (SAR). The objective of this study is to assess the role of the SAR on physical activity, play behavior, and toy-use behavior of children during free play.

Methods: Six children (5 females, Mage = 3.6 ± 1.9 years) participated in the majority of our pilot study’s seven 30-minute-long weekly play sessions (4 baseline and 3 intervention). During baseline sessions, the SAR was powered off. During intervention sessions, the SAR was teleoperated to move in the play area and offered rewards of lights, sounds, and bubbles to children. Thirty-minute videos of the play sessions were annotated using a momentary time sampling observation system. Mean percentage of time spent in behaviors of interest in baseline and intervention sessions were calculated. Paired-Wilcoxon signed rank tests were conducted to assess differences between baseline and intervention sessions.

Results: There was a significant increase in children’s standing (∼15%; Z = −2.09; p = 0.037) and a tendency for less time sitting (∼19%; Z = −1.89; p = 0.059) in the intervention phase as compared to the baseline phase. There was also a significant decrease (∼4.5%, Z = −2.70; p = 0.007) in peer interaction play and a tendency for greater (∼4.5%, Z = −1.89; p = 0.059) interaction with adults in the intervention phase as compared to the baseline phase. There was a significant increase in children’s interaction with the robot (∼11.5%, Z = −2.52; p = 0.012) in the intervention phase as compared to the baseline phase.

Conclusion: These results may indicate that a mobile SAR provides affordances through rewards that elicit children’s interaction with the SAR and more time standing in free play. This pilot study lays a foundation for exploring the role of SARs in inclusive play environments for children with and without mobility disabilities in real-world settings like day-care centers and preschools.

The development of autonomous legged/wheeled robots with the ability to navigate and execute tasks in unstructured environments is a well-known research challenge. In this work we introduce a methodology that permits a hybrid legged/wheeled platform to realize terrain traversing functionalities that are adaptable, extendable and can be autonomously selected and regulated based on the geometry of the perceived ground and associated obstacles. The proposed methodology makes use of a set of terrain traversing primitive behaviors that are used to perform driving, stepping on, down and over and can be adapted, based on the ground and obstacle geometry and dimensions. The terrain geometrical properties are first obtained by a perception module, which makes use of point cloud data coming from the LiDAR sensor to segment the terrain in front of the robot, identifying possible gaps or obstacles on the ground. Using these parameters the selection and adaption of the most appropriate traversing behavior is made in an autonomous manner. Traversing behaviors can be also serialized in a different order to synthesise more complex terrain crossing plans over paths of diverse geometry. Furthermore, the proposed methodology is easily extendable by incorporating additional primitive traversing behaviors into the robot mobility framework and in such a way more complex terrain negotiation capabilities can be eventually realized in an add-on fashion. The pipeline of the above methodology was initially implemented and validated on a Gazebo simulation environment. It was then ported and verified on the CENTAURO robot enabling the robot to successfully negotiate terrains of diverse geometry and size using the terrain traversing primitives.