Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Tsoi, Nathan"'
Multiclass neural network classifiers are typically trained using cross-entropy loss. Following training, the performance of this same neural network is evaluated using an application-specific metric based on the multiclass confusion matrix, such as
Externí odkaz:
http://arxiv.org/abs/2405.20954
Preference learning has long been studied in Human-Robot Interaction (HRI) in order to adapt robot behavior to specific user needs and desires. Typically, human preferences are modeled as a scalar function; however, such a formulation confounds criti
Externí odkaz:
http://arxiv.org/abs/2403.19795
Autor:
Zhang, Qiping, Tsoi, Nathan, Choi, Booyeon, Tan, Jie, Chiang, Hao-Tien Lewis, Vázquez, Marynel
Human impressions of robot performance are often measured through surveys. As a more scalable and cost-effective alternative, we study the possibility of predicting people's impressions of robot behavior using non-verbal behavioral cues and machine l
Externí odkaz:
http://arxiv.org/abs/2310.11590
Autor:
Francis, Anthony, Pérez-D'Arpino, Claudia, Li, Chengshu, Xia, Fei, Alahi, Alexandre, Alami, Rachid, Bera, Aniket, Biswas, Abhijat, Biswas, Joydeep, Chandra, Rohan, Chiang, Hao-Tien Lewis, Everett, Michael, Ha, Sehoon, Hart, Justin, How, Jonathan P., Karnan, Haresh, Lee, Tsang-Wei Edward, Manso, Luis J., Mirksy, Reuth, Pirk, Sören, Singamaneni, Phani Teja, Stone, Peter, Taylor, Ada V., Trautman, Peter, Tsoi, Nathan, Vázquez, Marynel, Xiao, Xuesu, Xu, Peng, Yokoyama, Naoki, Toshev, Alexander, Martín-Martín, Roberto
A major challenge to deploying robots widely is navigation in human-populated environments, commonly referred to as social robot navigation. While the field of social navigation has advanced tremendously in recent years, the fair evaluation of algori
Externí odkaz:
http://arxiv.org/abs/2306.16740
Deploying interactive systems in-the-wild requires adaptability to situations not encountered in lab environments. Our work details our experience about the impact of architecture choice on behavior reusability and reactivity while deploying a public
Externí odkaz:
http://arxiv.org/abs/2302.00191
Evaluation of social robot navigation inherently requires human input due to its qualitative nature. Motivated by the need to scale human evaluation, we propose a general method for deploying interactive, rich-client robotic simulations on the web. P
Externí odkaz:
http://arxiv.org/abs/2012.12336
Social navigation research is performed on a variety of robotic platforms, scenarios, and environments. Making comparisons between navigation algorithms is challenging because of the effort involved in building these systems and the diversity of plat
Externí odkaz:
http://arxiv.org/abs/2009.04300
While neural network binary classifiers are often evaluated on metrics such as Accuracy and $F_1$-Score, they are commonly trained with a cross-entropy objective. How can this training-evaluation gap be addressed? While specific techniques have been
Externí odkaz:
http://arxiv.org/abs/2009.01367
Autor:
Swofford, Mason, Peruzzi, John Charles, Tsoi, Nathan, Thompson, Sydney, Martín-Martín, Roberto, Savarese, Silvio, Vázquez, Marynel
We propose a data-driven approach to detect conversational groups by identifying spatial arrangements typical of these focused social encounters. Our approach uses a novel Deep Affinity Network (DANTE) to predict the likelihood that two individuals i
Externí odkaz:
http://arxiv.org/abs/1907.12910
Autor:
Rezatofighi, Hamid, Tsoi, Nathan, Gwak, JunYoung, Sadeghian, Amir, Reid, Ian, Savarese, Silvio
Intersection over Union (IoU) is the most popular evaluation metric used in the object detection benchmarks. However, there is a gap between optimizing the commonly used distance losses for regressing the parameters of a bounding box and maximizing t
Externí odkaz:
http://arxiv.org/abs/1902.09630