A5027790975- Social Robot Interaction and HRI
- Human-Automation Interaction and Safety
- Autonomous Vehicle Technology and Safety
- Multimodal Machine Learning Applications
- Human Pose and Action Recognition
- Evacuation and Crowd Dynamics
- Video Surveillance and Tracking Methods
- Advanced Image and Video Retrieval Techniques
- Older Adults Driving Studies
- Anomaly Detection Techniques and Applications
- Virtual Reality Applications and Impacts
- Gaze Tracking and Assistive Technology
- Visual perception and processing mechanisms
- Tactile and Sensory Interactions
- Traffic and Road Safety
- Innovative Human-Technology Interaction
- AI in Service Interactions
- Machine Learning and Data Classification
- Robotics and Automated Systems
- Advanced Neural Network Applications
- Hand Gesture Recognition Systems
Carnegie Mellon University
2020-2024
Indian Institute of Science Bangalore
2017
Indian Institute of Technology Guwahati
2015
The human-robot interaction community has developed many methods for robots to navigate safely and socially alongside humans. However, experimental procedures evaluate these works are usually constructed on a per-method basis. Such disparate evaluations make it difficult compare the performance of such across literature. To bridge this gap, we introduce SocNavBench , simulation framework evaluating social navigation algorithms. comprises simulator with photo-realistic capabilities curated...
The ability to semantically interpret hand-drawn line sketches, although very challenging, can pave way for novel applications in multimedia. We propose SKETCHPARSE, the first deep-network architecture fully automatic parsing of freehand object sketches. SKETCHPARSE is configured as a two-level convolutional network. level contains shared layers common all categories. second number expert sub-networks. Each specializes sketches from categories which contain structurally similar parts....
A major challenge to deploying robots widely is navigation in human-populated environments, commonly referred as social robot navigation. While the field of has advanced tremendously recent years, fair evaluation algorithms that tackle remains hard because it involves not just robotic agents moving static environments but also dynamic human and their perceptions appropriateness behavior. In contrast, clear, repeatable, accessible benchmarks have accelerated progress fields like computer...
Simulators are an essential tool for behavioural and interaction research on driving, due to the safety, cost, experimental control issues of on-road driving experiments. The most advanced simulators use expensive 360 degree projections systems ensure visual fidelity, full field view, immersion. However, similar fidelity can be achieved affordably using a virtual reality (VR) based interface. We present DReye VR, open-source VR simulator platform designed with priorities in mind. DReyeVR...
A major challenge to deploying robots widely is navigation in human-populated environments, commonly referred as social robot . While the field of has advanced tremendously recent years, fair evaluation algorithms that tackle remains hard because it involves not just robotic agents moving static environments but also dynamic human and their perceptions appropriateness behavior. In contrast, clear, repeatable, accessible benchmarks have accelerated progress fields like computer vision,...
Many intelligent driver assistance algorithms try to improve on-road safety by using eye gaze, commonly foveal gaze as an estimate of human attention. While visual acuity is highest in the field view, drivers often use their peripheral vision process scene elements. Previous work psychology has modeled this combination and a construct known Functional Field View (FFoV). In work, we study shape dynamics FFoV during active driving. We detection task virtual reality (VR) driving simulator with...
The ability to semantically interpret hand-drawn line sketches, although very challenging, can pave way for novel applications in multimedia. We propose SketchParse, the first deep-network architecture fully automatic parsing of freehand object sketches. SketchParse is configured as a two-level convolutional network. level contains shared layers common all categories. second number expert sub-networks. Each specializes sketches from categories which contain structurally similar parts....
Recently, pedestrian behavior research has shifted towards machine learning based methods and converged on the topic of modeling interactions. For this, a large-scale dataset that contains rich information is needed. We propose data collection system portable, which facilitates accessible in diverse environments. also couple with semi-autonomous labeling pipeline for fast trajectory label production. further introduce first batch from ongoing effort -- TBD dataset. Compared existing...
Advanced Driver Assistance Systems (ADAS) alert drivers during safety-critical scenarios but often provide superfluous alerts due to a lack of consideration for drivers' knowledge or scene awareness. Modeling these aspects together in data-driven way is challenging the scarcity critical scenario data with in-cabin driver state and world recorded together. We explore benefits modeling context Forward Collision Warning (FCW) systems. Working real-world video dataset on-road FCW deployments, we...
Simulators are an essential tool for behavioural and interaction research on driving, due to the safety, cost, experimental control issues of on-road driving experiments. The most advanced simulators use expensive 360 degree projections systems ensure visual fidelity, full field view, immersion. However, similar fidelity can be achieved affordably using a virtual reality (VR) based interface. We present DReyeVR, open-source VR simulator platform designed with priorities in mind. DReyeVR...
The human-robot interaction (HRI) community has developed many methods for robots to navigate safely and socially alongside humans. However, experimental procedures evaluate these works are usually constructed on a per-method basis. Such disparate evaluations make it difficult compare the performance of such across literature. To bridge this gap, we introduce SocNavBench, simulation framework evaluating social navigation algorithms. SocNavBench comprises simulator with photo-realistic...
The ability to identify important objects in a complex and dynamic driving environment is essential for autonomous agents make safe efficient decisions. It also helps assistive systems decide when alert drivers. We tackle object importance estimation data-driven fashion introduce HOIST - Human-annotated Object Importance Simulated Traffic. contains scenarios with human-annotated labels vehicles pedestrians. additionally propose novel approach that relies on counterfactual reasoning estimate...