Abstract We present a data-driven algorithm to model and predict the socio-emotional impact of groups on observers. Psychological research finds that highly entitative i.e. cohesive and uniform groups induce threat and unease in observers. Our algorithm models realistic trajectory-level behaviors to classify and map the motion-based entitativity of crowds. This mapping is based on a statistical scheme that dynamically learns pedestrian behavior and computes the resultant entitativity induced emotion through group motion characteristics.
Abstract We present a data-driven algorithm to model and predict the socio-emotional impact of groups on observers. Psychological research finds that highly entitative i.e. cohesive and uniform groups induce threat and unease in observers. Our algorithm models realistic trajectory-level behaviors to classify and map the motion-based entitativity of crowds. This mapping is based on a statistical scheme that dynamically learns pedestrian behavior and computes the resultant entitativity induced emotion through group motion characteristics.
Abstract In this paper, we present a novel Heavy-Tailed Stochastic Policy Gradient (HT-PSG) algorithm to deal with the challenges of sparse rewards in continuous control problems. Sparse rewards are common in continuous control robotics tasks such as manipulation and navigation and make the learning problem hard due to the non-trivial estimation of value functions over the state space. This demands either reward shaping or expert demonstrations for the sparse reward environment.
Authors: Laura Zheng, Sanghyun Son, Jing Liang, Xijun Wang, Brian Clipp, Ming Lin
Paper Code IROS 2024 Github (Under Construction)
– Abstract In trajectory forecasting tasks for traffic, future output trajectories can be computed by advancing the ego vehicle’s state with predicted actions according to a kinematics model. By unrolling predicted trajectories via time integration and models of kinematic dynamics, predicted trajectories should not only be kinematically feasible but also relate uncertainty from one timestep to the next.
Abstract We present DenseCAvoid, a novel algorithm for navigating a robot through dense crowds and avoiding collisions by anticipating pedestrian behaviors. Our formulation uses visual sensors and a pedestrian trajectory prediction algorithm to track pedestrians in a set of input frames and compute bounding boxes that extrapolate to the pedestrian positions in a future time. Our hybrid approach combines this trajectory prediction with a Deep Reinforcement Learning-based collision avoidance method to train a policy to generate smoother, safer, and more robust trajectories during run-time.
Paper Code Dataset DensePeds, IROS’19 GitHub Link. India-Walk (More details below).
We present a pedestrian tracking algorithm, DensePeds, that tracks individuals in highly dense crowds (greater than 2 pedestrians per square meter). Our approach is designed for videos captured from front-facing or elevated cameras. We present a new motion model called Front-RVO (FRVO) for predicting pedestrian movements in dense situations using collision avoidance constraints and combine it with state-of-the-art Mask R-CNN to compute sparse feature vectors that reduce the loss of pedestrian tracks (false negatives).
Overview Rural populations are highly vulnerable to behavioral health problems during the COVID-19 pandemic. Rural children have higher rates of behavioral disorders and more severe symptoms than urban youth, and rural families experience higher rates of poverty, health problems, and addictions, which are further challenged by poor access to care and scarce community resources. Community telehealth behavioral services delivered to the home via videoconferencing systems have become the most available and safest option for child behavioral treatment during the COVID-19 pandemic.
Overview Rural populations are highly vulnerable to behavioral health problems during the COVID-19 pandemic. Rural children have higher rates of behavioral disorders and more severe symptoms than urban youth, and rural families experience higher rates of poverty, health problems, and addictions, which are further challenged by poor access to care and scarce community resources. Community telehealth behavioral services delivered to the home via videoconferencing systems have become the most available and safest option for child behavioral treatment during the COVID-19 pandemic.
– Abstract BACKGROUND: Patient engagement is a critical but challenging public health priority in behavioral healthcare. During telehealth sessions, healthcare providers need to rely more on verbal strategies than typical non-verbal cues to engage patients. Hence, the typical patient engagement behaviors are now different, and provider training on telehealth patient engagement is unavailable or quite limited. Therefore, we explore the application of machine learning for estimating patient engagement to assist psychotherapists in better diagnosis of mental disorders during telemental health sessions.
Abstract We propose a differentiable cloth simulator that can be embedded as a layer in deep neural networks. This approach provides an effective, robust framework for modeling cloth dynamics, self-collisions, and contacts. Due to the high dimensionality of the dynamical system in modeling cloth, traditional gradient computation for collision response can become impractical. To address this problem, we propose to compute the gradient directly using QR decomposition of a much smaller matrix.