Raymond Liu

Raymond Liu, Patrick Slade

Globally, 340 million people have blindness or moderate to severe visual impairment (BVI)$^1$ which limits independent outdoor navigation$^2$ and negatively affects their health and quality of life$^{3,4}$. We surveyed 112 people with BVI and found that an ideal outdoor navigation aid must be able to perform turn-by-turn directions, path guidance, and obstacle detection and avoidance. Existing navigation tools such as white canes, guide dogs, and electronic travel aids often lack one or more of these criteria and may be expensive or inaccessible$^{5,6}$. Here we introduce Mobilio, a smartphone application that incorporates machine learning, sensor fusion algorithms, and personalized audio feedback to meet all of the outdoor navigation criteria. The reliability of the smartphone sensors and models used for navigation were assessed with engineering tests in representative navigation scenarios. We performed a series of experiments where Mobilio personalized audio feedback for participants with BVI (n = 14), guided them along an outdoor community path, and helped them navigate an obstacle course. Participants walking with Mobilio and a white cane reduced time to navigate a community path by 13 $\pm$ 3% and environmental contacts by 41 $\pm$ 5% compared to using Google Maps and a white cane. Mobilio achieved similar outdoor navigation reliability as a human guide. Participant surveys reported that Mobilio was easy to use, had a low perceived workload, and provided intuitive audio feedback. This work provides an accessible and personalized tool that may be an effective outdoor navigation aid to increase independence for people with BVI.

Shreshth Rajan, Raymond Liu

Semantic segmentation of outdoor street scenes plays a key role in applications such as autonomous driving, mobile robotics, and assistive technology for visually-impaired pedestrians. For these applications, accurately distinguishing between key surfaces and objects such as roads, sidewalks, vehicles, and pedestrians is essential for maintaining safety and minimizing risks. Semantic segmentation must be robust to different environments, lighting and weather conditions, and sensor noise, while being performed in real-time. We propose a region-level, uncertainty-gated retrieval mechanism that improves segmentation accuracy and calibration under domain shift. Our best method achieves an 11.3% increase in mean intersection-over-union while reducing retrieval cost by 87.5%, retrieving for only 12.5% of regions compared to 100% for always-on baseline.

Jules Watson, Xi Wang, Raymond Liu et al.

Within the common LLM use case of text revision, we study LLMs' revision of gendered role nouns (e.g., outdoorsperson/woman/man) and their justifications of such revisions. We evaluate their alignment with feminist and trans-inclusive language reforms for English. Drawing on insight from sociolinguistics, we further assess if LLMs are sensitive to the same contextual effects in the application of such reforms as people are, finding broad evidence of such effects. We discuss implications for value alignment.