Search

Finding a path free from obstacles that poses minimal risk is critical for safe navigation. People who are sighted and people who are visually impaired require navigation safety while walking on a sidewalk. In this research we developed an assistive navigation on a sidewalk by integrating sensory inputs using reinforcement learning. We trained a Sidewalk Obstacle Avoidance Agent (SOAA) through reinforcement learning in a simulated robotic environment. A Sidewalk Obstacle Conversational Agent (SOCA) is built by training a natural language conversation agent with real conversation data. The SOAA along with SOCA was integrated in a prototype device called augmented guide (AG). Empirical analysis showed that this prototype improved the obstacle avoidance experience about 5% from a base case of 81.29%, Comment: Journal, to be submitted

Situational awareness is a critical foundation for the protection of human life/properties and is challenging to maintain for people with disabilities (i.e., visual impairments and limited mobility). In this paper, we present a dialog enabled end-to-end assistive solution called "SafeAccess" to build a safer smart home by providing situational awareness. The key functions of SafeAccess are: - 1) monitoring homes and identifying incoming persons; 2) helping users in assessing incoming threats (e.g., burglary, robbery, gun violence); and, 3) allowing users to grant safe access to homes for friends/families. In this work, we focus on building a robust model for detecting and recognizing person, generating image descriptions, and designing a prototype for the smart door. To interact with the system, we implemented a dialog enabled smartphone app, especially for creating a personalized profile from face images or videos of friends/families. A Raspberry pi connected to the home monitoring cameras captures the video frames and performs change detection to identify frames with activities. Then, we detect human presence using Faster r-cnn and extract faces using Multi-task Cascaded Convolutional Networks (MTCNN). Subsequently, we match the detected faces using FaceNet/support vector machine (SVM) classifiers. The system notifies users with an MMS containing the name of incoming persons or as "unknown", scene image, facial description, and contextual information. The users can grant access or call emergency services using the SafeAccess app based on the received notification. Our system identifies persons with an F-score 0.97 and recognizes items to generate image description with an average F-score 0.97.

An assistive solution to assess incoming threats (e.g., robbery, burglary, gun violence) for homes will enhance the safety of the people with or without disabilities. This paper presents "SafeNet"- an integrated assistive system to generate context-oriented image descriptions to assess incoming threats. The key functionality of the system includes the detection and identification of human and generating image descriptions from the real-time video streams obtained from the cameras placed in strategic locations around the house. In this paper, we focus on developing a robust model called "SafeNet" to generate image descriptions. To interact with the system, we implemented a dialog enabled interface for creating a personalized profile from face images or videos of friends/families. To improve computational efficiency, we apply change detection to filter out frames that do not have any activity and use Faster-RCNN to detect the human presence and extract faces using Multitask Cascaded Convolutional Networks (MTCNN). Subsequently, we apply LBP/FaceNet to identify a person. SafeNet sends image descriptions to the users with an MMS containing a person's name if any match found or as "Unknown", scene image, facial description, and contextual information. SafeNet identifies friends/families/caregiver versus intruders/unknown with an average F-score 0.97 and generates image descriptions from 10 classes with an average F-measure 0.97., Comment: arXiv admin note: text overlap with arXiv:1904.01178