We consider the setting where a robot must complete a sequence of tasks in a persistent large-scale environment, given one at a time. Existing task planners often operate myopically, focusing solely on immediate goals without considering the impact of current actions on future tasks. Anticipatory planning, which reduces the joint objective of the immediate planning cost of the current task and the expected cost associated with future subsequent tasks, offers an approach for improving long-lived task planning. However, applying anticipatory planning in large-scale environments presents significant challenges due to the sheer number of assets involved, which strains the scalability of learning and planning. In this research, we introduce a model-based anticipatory task planning framework designed to scale to large-scale realistic environments. Our framework uses a graph neural network (GNN) in particular via a representation inspired by a 3D scene graph to learn the essential properties of the environment crucial to estimating the state's expected cost and a samplingbased procedure for practical large-scale anticipatory planning. Our experimental results show that our planner reduces the cost of task sequence by$\mathbf{5. 3 8 \%}$in home and$\mathbf{3 1. 5 \%}$in restaurant settings. If given time to prepare in advance using our model reduces task sequence costs by$\mathbf{4 0. 6 \%}$and$\mathbf{4 2. 5 \%}$, respectively.

We address the task of long-horizon navigation in partially mapped environments for which active gathering of information about faraway unseen space is essential for good behavior. We present a novel planning strategy that, at training time, affords tractable computation of the value of information associated with revealing potentially informative regions of unseen space, data used to train a graph neural network to predict the goodness of temporally-extended exploratory actions. Our learning-augmented model-based planning approach predicts the expected value of information of revealing unseen space and is capable of using these predictions to actively seek information and so improve long-horizon navigation. Across two simulated office-like environments, our planner outperforms competitive learned and non-learned baseline navigation strategies, achieving improvements of up to 63.76% and 36.68%, demonstrating its capacity to actively seek performance-critical information.

We improve reliable, long-horizon, goal-directed navigation in partially-mapped environments by using nonlocally available information to predict the goodness of temporally-extended actions that enter unseen space. Making predictions about where to navigate in general requires nonlocal information: any observations the robot has seen so far may provide information about the goodness of a particular direction of travel. Building on recent work in learning-augmented model-based planning under uncertainty, we present an approach that can both rely on nonlocal information to make predictions (via a graph neural network) and is reliable by design: it will always reach its goal, even when learning does not provide accurate predictions. We conduct experiments in three simulated environments in which nonlocal information is needed to perform well. In our large scale university building environment, generated from real-world floorplans to the scale, we demonstrate a 9.3% reduction in cost-to-go compared to a non-learned baseline and a 14.9% reduction compared to a learning-informed planner that can only use local information to inform its predictions.

Through Facebook "Group" feature, users often sensitize communionships, join different Facebook groups, and establish imagined communities with known people and strangers. In our interview study with 32 admins and users of Facebook groups, we explored the influential factors of such communionships, the challenges the Facebook group admins face while managing these communities, and how they resolve those. Our findings show that admins set rules for the entry and maintenance of the groups, monitor members' activities, and often limit their actions or mute them during conflicts. Thus, the members and admins of the groups together grow a sensibility of sovereignty within the community on Facebook. While the imagined sovereignty in Facebook groups is empowering, this empowerment may not be perceived and experienced evenly by everyone in such online communities. To explain this, we build on the concept of "Imagined Communities' by Benedict Anderson [16 ] and argue that there is a tension between Facebook admins' perceived sovereignty and other users' empowerment in practice. Our work joins the body of CSCW literature that aims at designing more sustainable and collaborative tools for specific communities on Facebook groups and other similar platforms.

Facebook users often join Facebook groups to connect to the people with the same interest regardless of the fact that the other members take the same standing with them. Our study aims to investigate Bangladeshi users' motivation to join and strategies to manage their Facebook groups and identify the relevant challenges. In our ongoing work, we are conducting a survey and interviewing Facebook-group users to understand how Facebook groups are bringing the users of similar interest and agenda together on Facebook and providing the admins with imagined sovereignty. This poster presents some of our crucial findings. This set of findings will be useful in designing better tools for managing Facebook groups for empowering the admins and the users.