arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.08321cs.HCcs.CV

ChatGPT能否辅助视障人士完成微导航?

Can ChatGPT assist visually impaired people with micro-navigation?

Chongqing University(重庆大学);Schepens Eye Research Institute of Mass Eye & Ear(麻省眼耳医院Schepens眼科研究所);Harvard Medical School(哈佛医学院)

Junxian He, Shrinivas Pundlik, Gang Luo

AI总结:

本研究构建微导航场景测试集,评估不同输入与提示条件下ChatGPT 4o的视障微导航辅助性能,发现人工文本描述输入可显著提升效果,指出优化场景理解后多模态聊天机器人有望用于该场景。

摘要:

研究目的:微导航对盲人和视障人群而言存在挑战,他们常需向明眼人求助。本研究探讨了将ChatGPT用作虚拟助手提供导航指引的可行性。研究方法:我们构建了包含室内外微导航场景的测试集,涵盖113张场景图像及对应的人工生成文本描述;基于这些场景整理了412个寻路查询及其预期回复。并非所有查询都能依据场景图像中的可用信息作答,无法作答的查询预期回复为“我不知道”,作为负样本。研究要求模型给出高层级的方向回复,无需分步指引。我们在不同条件下,基于灵敏度(SEN)和特异度(SPE)评估了ChatGPT 4o的性能。研究结果:默认设置下,以场景图像为输入的ChatGPT 4o的灵敏度和特异度分别为64.8%和75.9%;针对无法作答的问题给出回复指令后,灵敏度未显著提升,但特异度提高了约14个百分点;当输入替换为人工撰写的场景描述而非图像时,灵敏度和特异度均大幅提升,平均分别提高约17和16个百分点;当输入为文本描述时,向助手提供进一步的提示指令并未显著改变灵敏度和特异度数值。研究结论:当前原生ChatGPT 4o在部分场景下仍无法提供正确的微导航指引,可能原因是其场景理解能力未针对导航用途优化。若多模态聊天机器人能以媲美人类的清晰度解读场景,且有合适的提示引导,便有望为视障人士提供微导航辅助。

英文摘要:

Objective: Micro-navigation poses challenges for blind and visually impaired individuals. They often need to ask for sighted assistance. We explored the feasibility of utilizing ChatGPT as a virtual assistant to provide navigation directions. Methods: We created a test set of outdoor and indoor micro-navigation scenarios consisting of 113 scene images and their human-generated text descriptions. A total of 412 way-finding queries and their expected responses were compiled based on the scenarios. Not all queries are answerable based on the information available in the scene image. "I do not know"response was expected for unanswerable queries, which served as negative cases. High level orientation responses were expected, and step-by-step guidance was not required. ChatGPT 4o was evaluated based on sensitivity (SEN) and specificity (SPE) under different conditions. Results: The default ChatGPT 4o, with scene images as inputs, resulted in SEN and SPE values of 64.8% and 75.9%, respectively. Instruction on how to respond to unanswerable questions did not improve SEN substantially but SPE increased by around 14 percentage points. SEN and SPE both improved substantially, by about 17 and 16 percentage points on average respectively, when human written descriptions of the scenes were provided as input instead of images. Providing further prompt instructions to the assistants when the input was text description did not substantially change the SEN and SPE values. Conclusion: Current native ChatGPT 4o is still unable to provide correct micro-navigation guidance in some cases, probably because its scene understanding is not optimized for navigation purposes. If multi-modal chatbots could interpret scenes with a level of clarity comparable to humans, and also guided by appropriate prompts, they may have the potential to provide assistance to visually impaired for micro-navigation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑