Robots Enact Malignant Stereotypes
Andrew Hundt, William Agnew, Vicky Zeng, Severin Kacianka, Matthew, Gombolay

TL;DR
This paper investigates how large dataset-driven robotic systems can physically enact harmful stereotypes related to race, gender, and physiognomy, revealing significant biases and calling for safer, more just development practices.
Contribution
It provides the first systematic evaluation of stereotype manifestation in autonomous robots powered by foundation models like CLIP, highlighting the risks and proposing policy and research directions.
Findings
Robots exhibit toxic stereotypes related to race and gender.
Robots are less likely to recognize Women and People of Color.
Large datasets and foundation models can amplify harmful stereotypes in robotics.
Abstract
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.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsCLIPort · Contrastive Language-Image Pre-training
