Evaluation of Socially-Aware Robot Navigation

Gao, Yuxiang; Huang, Chien-Ming

doi:10.3389/frobt.2021.721317

Cited by 45 publications

(38 citation statements)

References 174 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Embodied service robots in general are touted as means to reorganize businesses and replace many jobs, such as hospital supply management, pharmaceutical dispensing, cleaners, waiters, guides, police, and butlers [33,34,76].…”

Section: Motivation Related Work and Interdisciplinary Synthesismentioning

confidence: 99%

Robots Enact Malignant Stereotypes

Hundt

Agnew

Zeng

et al. 2022

2022 ACM Conference on Fairness, Accountability, and Transparency

View full text Add to dashboard Cite

Stereotypes, bias, and discrimination have been extensively documented in Machine Learning (ML) methods such as Computer Vision (CV) [18,80], Natural Language Processing (NLP) [6], or both, in the case of large image and caption models such as OpenAI CLIP [14].In this paper, we evaluate how ML bias manifests in robots that physically and autonomously act within the world. We audit one of several recently published CLIP-powered robotic manipulation methods, presenting it with objects that have pictures of human faces on the surface which vary across race and gender, alongside task descriptions that contain terms associated with common stereotypes.Our experiments definitively show robots acting out toxic stereotypes with respect to gender, race, and scientifically-discredited physiognomy, at scale. Furthermore, the audited methods are less likely to recognize Women and People of Color. Our interdisciplinary sociotechnical analysis synthesizes across fields and applications such as Science Technology and Society (STS), Critical Studies, History, Safety, Robotics, and AI. We find that robots powered by large datasets and Dissolution Models (sometimes called "foundation models", e.g. CLIP) that contain humans risk physically amplifying malignant stereotypes in general; and that merely correcting disparities will be insufficient for the complexity and scale of the problem. Instead, we recommend that robot learning methods that physically manifest stereotypes or other harmful outcomes be paused, reworked, or even wound down when appropriate, until outcomes can be proven safe, effective, and just. Finally, we discuss comprehensive policy changes and the potential of new interdisciplinary research on topics like Identity Safety Assessment Frameworks and Design Justice to better understand and address these harms.

show abstract

Section: Motivation Related Work and Interdisciplinary Synthesismentioning

confidence: 99%

Robots Enact Malignant Stereotypes

Hundt

Agnew

Zeng

et al. 2022

2022 ACM Conference on Fairness, Accountability, and Transparency

View full text Add to dashboard Cite

show abstract

“…Due to the lack of sufficiently large datasets, these models often train in simulators that lack realistic pedestrian behavior. Apart from training, datasets are also increasing in popularity in social navigation evaluation due to their realistic pedestrian behavior [14]. Social navigation methods are often evaluated in environments using pedestrian data trajectory playback (e.g., [41], [7], [38], [44]).…”

Section: A Pedestrian Data In Researchmentioning

confidence: 99%

“…Social navigation methods are often evaluated in environments using pedestrian data trajectory playback (e.g., [41], [7], [38], [44]). However, similar to human motion prediction research, these evaluations are typically only conducted on the ETH [31] and UCY [20] datasets as shown by [14]. These two datasets only use overhead views, and therefore lack the perspective view used by most robots.…”

Section: A Pedestrian Data In Researchmentioning

confidence: 99%

Towards Rich, Portable, and Large-Scale Pedestrian Data Collection

Wang¹,

Biswas²,

Admoni³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recently, pedestrian behavior research has shifted towards machine learning based methods and converged on the topic of modeling pedestrian interactions. For this, a large-scale dataset that contains rich information is needed. We propose a data collection system that is portable, which facilitates accessible large-scale data collection in diverse environments. We also couple the system with a semi-autonomous labeling pipeline for fast trajectory label production. We demonstrate the effectiveness of our system by further introducing a dataset we have collected -the TBD pedestrian dataset. Compared with existing pedestrian datasets, our dataset contains three components: human verified labels grounded in the metric space, a combination of top-down and perspective views, and naturalistic human behavior in the presence of a socially appropriate "robot". In addition, the TBD pedestrian dataset is larger in quantity compared to similar existing datasets and contains unique pedestrian behavior.

show abstract

“…3) Lack of diverse pedestrian models: All simulators except SocNavBench suffer from homogeneity as they deploy one fixed mathematical model for all pedestrians in the scene. Since the behavior of humans differ depending upon their age, demographics, gender and culture [54], [55], [56], a single pedestrian model applied to all human models is not a realistic representation of human population, especially in the public places like hospitals, airports, hotels, etc. SocNavBench is an exception as it is rooted in the real pedestrian data for simulating pedestrian behavior.…”

Section: Challengesmentioning

confidence: 99%

Simulators for Mobile Social Robots:State-of-the-Art and Challenges

Kaur¹,

Liu²,

Shi³

2022

Preprint

View full text Add to dashboard Cite

The future robots are expected to work in a shared physical space with humans [1], however, the presence of humans leads to a dynamic environment that is challenging for mobile robots to navigate. The path planning algorithms designed to navigate a collision free path in complex human environments are often tested in real environments due to the lack of simulation frameworks. This paper identifies key requirements for an ideal simulator for this task, evaluates existing simulation frameworks and most importantly, it identifies the challenges and limitations of the existing simulation techniques.First and foremost, we recognize that the simulators needed for the purpose of testing mobile robots designed for human environments are unique as they must model realistic pedestrian behavior in addition to the modelling of mobile robots. Our study finds that Pedsim ros [2] and a more recent SocNavBench framework [3] are the only two 3D simulation frameworks that meet most of the key requirements defined in our paper. In summary, we identify the need for developing more simulators that offer an ability to create realistic 3D pedestrian rich virtual environments along with the flexibility of designing complex robots and their sensor models from scratch.

show abstract

Evaluation of Socially-Aware Robot Navigation

Cited by 45 publications

References 174 publications

Robots Enact Malignant Stereotypes

Robots Enact Malignant Stereotypes

Towards Rich, Portable, and Large-Scale Pedestrian Data Collection

Simulators for Mobile Social Robots:State-of-the-Art and Challenges

Contact Info

Product

Resources

About