Interaction Needs and Opportunities for Failing Robots

Morales, Cecilia G.; Carter, Elizabeth; Tan, Xiang Zhi; Steinfeld, Aaron

doi:10.1145/3322276.3322345

Cited by 20 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Correia et al [22] has found a decrease in trustworthiness when robots fail, however, the effect is mitigated if the robot attributes the failure to a technical problem. Mitigation strategies depend on several factors, such as the nature of the task [51], failure timing [53] and failure severity [61].…”

Section: Robot Failuresmentioning

confidence: 99%

“…Finally, less work has been done on failure in high severity situations, as this is difficult to convincingly simulate in a laboratory environment. In that direction, Morales et al [61] studied people's behaviour to robot failures that involve personal risk. Providing a human-like face showed to influence people's willingness to help the robot.…”

Section: Robot Failuresmentioning

confidence: 99%

See 1 more Smart Citation

Grounding behaviours with conversational interfaces: effects of embodiment and failures

Kontogiorgos

Pereira

Gustafson

2021

J Multimodal User Interfaces

View full text Add to dashboard Cite

Conversational interfaces that interact with humans need to continuously establish, maintain and repair common ground in task-oriented dialogues. Uncertainty, repairs and acknowledgements are expressed in user behaviour in the continuous efforts of the conversational partners to maintain mutual understanding. Users change their behaviour when interacting with systems in different forms of embodiment, which affects the abilities of these interfaces to observe users’ recurrent social signals. Additionally, humans are intellectually biased towards social activity when facing anthropomorphic agents or when presented with subtle social cues. Two studies are presented in this paper examining how humans interact in a referential communication task with wizarded interfaces in different forms of embodiment. In study 1 (N = 30), we test whether humans respond the same way to agents, in different forms of embodiment and social behaviour. In study 2 (N = 44), we replicate the same task and agents but introduce conversational failures disrupting the process of grounding. Findings indicate that it is not always favourable for agents to be anthropomorphised or to communicate with non-verbal cues, as human grounding behaviours change when embodiment and failures are manipulated.

show abstract

Section: Robot Failuresmentioning

confidence: 99%

Section: Robot Failuresmentioning

confidence: 99%

Grounding behaviours with conversational interfaces: effects of embodiment and failures

Kontogiorgos

Pereira

Gustafson

2021

J Multimodal User Interfaces

View full text Add to dashboard Cite

show abstract

“…These works have revealed that humans are more likely to help robots that ask politely [42], provide justifications [6], indicate urgency [9], require less help [38], display emotion [13], offer people desired items [3], maintain appropriate interpersonal distance [46], establish smooth communication with the person [47], and are actively doing tasks for the person [1]. Others showed that humans are less likely to help robots while they are doing a primary task [26,18] or if they have been exposed to robot failures [33]. Yet other works found that microcultural factors (e.g., social atmosphere) influences whether humans help a robot [17] and that help-seeking robots had a higher perceived usability [30].…”

Section: B Human Responses To Help-seeking Behaviormentioning

confidence: 99%

Modeling Human Helpfulness with Individual and Contextual Factors for Robot Planning

Nanavati¹,

Mavrogiannis²,

Weatherwax³

et al. 2021

Robotics: Science and Systems XVII

View full text Add to dashboard Cite

Robots deployed in human-populated spaces often need human help to effectively complete their tasks. Yet, a robot that asks for help too frequently or at the wrong times may cause annoyance, and a robot that asks too infrequently may be unable to complete its tasks. In this paper, we present a model of humans' helpfulness towards a robot in an office environment, learnt from online user study data. Our key insight is that effectively planning for a task that involves bystander help requires disaggregating individual and contextual factors and explicitly reasoning about uncertainty over individual factors. Our model incorporates the individual factor of latent helpfulness and the contextual factors of human busyness and robot frequency of asking. We integrate the model into a Bayes-Adaptive Markov Decision Process (BAMDP) framework and run a user study that compares it to baseline models that do not incorporate individual or contextual factors. The results show that our model significantly outperforms baseline models by a factor of 1.5X, and it does so by asking for help more effectively: asking 1.2X times less while still receiving more human help on average. p ask Human 3 Human 1 tions help it. e model.

show abstract

“…A wide range of solution procedures can be taken into consideration. Research papers specify: heuristic methods that include constructive procedure, genetic algorithms, tabu search, simulated annealing, and ant colony optimization [ 43 , 44 , 45 , 46 ], optimum seeking models (branch and bound search, dynamic programming, linear, and integral programming) [ 47 , 48 ], other approaches (theory of constrains, knowledge-based approach, expert systems) [ 49 , 50 , 51 ], simulation methods [ 52 , 53 ]. …”

Section: Introductionmentioning

confidence: 99%

“…heuristic methods that include constructive procedure, genetic algorithms, tabu search, simulated annealing, and ant colony optimization [ 43 , 44 , 45 , 46 ],…”

Section: Introductionmentioning

confidence: 99%

Selection and Optimization of the Parameters of the Robotized Packaging Process of One Type of Product

Borys

Kaczmarek

Laskowski

2020

Sensors

View full text Add to dashboard Cite

The article presents the results of computer simulations related to the selection and optimization of the parameters of robotic packing process of one type of product. Taking the required performance of the robotic production line as a basis, we proposed its configuration using the RobotStudio environment for offline robot programming and virtual controller technology. Next, a methodology for the validation of the adopted assumptions was developed, based on a wide range of input data and a precise representation of the applicable conditions in the packaging process of one type of product. This methodology included test scenarios repeated an appropriate number of times in order to obtain the result data with the desired reliability and repeatability. The main element of the research was a computer simulation of the station based on the Picking PowerPac package. It was assumed that the products on the technological line are generated pseudo-randomly, thus reflecting the real working conditions. The result of the conducted works is the optimal operating speed of industrial robots and conveyors. The developed methodology allows for multifaceted analyses of the key parameters of the technological process (e.g., the number of active robots and their load, speed of conveyors, and station efficiency). We paid special attention to the occurrence of anomalies, i.e., emergency situations in the form of “halting” the operation of chosen robots and their impact on the obtained quality of the industrial process. As a result of the simulations, numerical values were obtained, maximum efficiency, with regard to maximum overflow of items of 5%, for LB algorithm was equal to 1188 completed containers per hour, with conveyors speeds of 270 mm/s and 165 mm/s. This efficiency was possible at robot speeds R1 = 6450 mm/s, R2 = 7500 mm/s, R3 = 6500 mm/s, R4 = 6375 mm/s, R5 = 5500 mm/s, R6 = 7200 mm/s. The ATC algorithm reached efficiency of 1332 containers per hour with less than 5% overflown items, with conveyor speeds of 310 mm/s and 185 mm/s. This efficiency was possible at robot speeds R1 = 7500 mm/s, R2 = 7500 mm/s, R3 = 7200 mm/s, R4 = 7000 mm/s, R5 = 6450 mm/s, R6 = 6300 mm/s. Tests carried out for emergency situations showed that the LB algorithm does not allow for automatic continuation of the process, while the ATC algorithm assured production efficiency of 94% to 98% of the maximum station efficiency.

show abstract

Interaction Needs and Opportunities for Failing Robots

Cited by 20 publications

References 21 publications

Grounding behaviours with conversational interfaces: effects of embodiment and failures

Grounding behaviours with conversational interfaces: effects of embodiment and failures

Modeling Human Helpfulness with Individual and Contextual Factors for Robot Planning

Selection and Optimization of the Parameters of the Robotized Packaging Process of One Type of Product

Contact Info

Product

Resources

About