We introduce a crowd simulation method that uses a block coordinate descent solver reminiscent of projective dynamics approaches. Existing projective dynamics work focuses on simulating deformable materials — which makes us the first to incorporate crowds into such framework. We simulate agents as nodes in a mass-spring system, where springs are created dynamically to simulate different crowd phenomena. We propose novel projective solutions for such springs to emulate time-to-collision avoidance behaviors. Our method encapsulates the collective response of the crowd using implicit Euler integration, while a conjugate gradient solver efficiently resolves the resulting mass-spring linear system to enable the simulation of large-scale, emergent crowd behaviors.

Abstract The need to plan motions for agents with variable shape constraints such as under different formations appears in several virtual and real‐world applications of autonomous agents. In this work, we focus on planning and execution of formation‐aware paths for a group of agents traversing a cluttered environment. The proposed planning framework addresses the trade‐off between being able to enforce a preferable formation when traversing the corridors of the environment, versus accepting to switch to alternative formations requiring less clearance in order to utilize narrower corridors that can lead to a shorter overall path to the final destination. At the planning stage, this trade‐off is addressed with a multi‐layer graph annotated with per‐layer navigation costs and formation transition costs, where each layer represents one formation together with its specific clearance requirement. At the navigation stage, we introduce Corridor Shortest Path Maps (CSPMs), which produce a vector field for guiding agents along the solution corridor, ensuring unobstructed in‐formation navigation in cluttered environments, as well as group motion along lengthwise‐optimal paths in the solution corridor. We also present examples of how our multi‐layer planning framework can be applied to other types of multi‐modal planning problems.

We address the problem of indoor layout synthesis, which is a topic of continuing research interest in computer graphics. The newest works made significant progress using data-driven generative methods; however, these approaches rely on suitable datasets. In practice, desirable layout properties may not exist in a dataset, for instance, specific expert knowledge can be missing in the data. We propose a method that combines expert knowledge, for example, knowledge about ergonomics, with a data-driven generator based on the popular Transformer architecture. The knowledge is given as differentiable scalar functions, which can be used both as weights or as additional terms in the loss function. Using this knowledge, the synthesized layouts can be biased to exhibit desirable properties, even if these properties are not present in the dataset. Our approach can also alleviate problems of lack of data and imperfections in the data. Our work aims to improve generative machine learning for modeling and provide novel tools for designers and amateurs for the problem of interior layout creation.

Abstract Creating realistic styled spaces is a complex task, which involves design know‐how for what furniture pieces go well together. Interior style follows abstract rules involving color, geometry and other visual elements. Following such rules, users manually select similar‐style items from large repositories of 3D furniture models, a process which is both laborious and time‐consuming. We propose a method for fast‐tracking style‐similarity tasks, by learning a furniture's style‐compatibility from interior scene images. Such images contain more style information than images depicting single furniture. To understand style, we train a deep learning network on a classification task. Based on image embeddings extracted from our network, we measure stylistic compatibility of furniture. We demonstrate our method with several 3D model style‐compatibility results, and with an interactive system for modeling style‐consistent scenes.

The arrangement of objects into a layout can be challenging for non-experts, as is affirmed by the existence of interior design professionals. Recent research into the automation of this task has yielded methods that can synthesize layouts of objects respecting aesthetic and functional constraints that are non-linear and competing. These methods usually adopt a stochastic optimization scheme, which samples from different layout configurations, a process that is slow and inefficient. We introduce an physics-motivated, continuous layout synthesis technique, which results in a significant gain in speed and is readily scalable. We demonstrate our method on a variety of examples and show that it achieves results similar to conventional layout synthesis based on Markov chain Monte Carlo (McMC) state-search, but is faster by at least an order of magnitude and can handle layouts of unprecedented size as well as tightly-packed layouts that can overwhelm McMC.

We introduce a biomimetic framework for human sensorimotor control, which features a biomechanically simulated human musculoskeletal model actuated by numerous muscles, with eyes whose retinas have nonuniformly distributed photoreceptors. The virtual human's sensorimotor control system comprises 20 trained deep neural networks (DNNs), half constituting the neuromuscular motor subsystem, while the other half compose the visual sensory subsystem. Directly from the photoreceptor responses, 2 vision DNNs drive eye and head movements, while 8 vision DNNs extract visual information required to direct arm and leg actions. Ten DNNs achieve neuromuscular control---2 DNNs control the 216 neck muscles that actuate the cervicocephalic musculoskeletal complex to produce natural head movements, and 2 DNNs control each limb; i.e., the 29 muscles of each arm and 39 muscles of each leg. By synthesizing its own training data, our virtual human automatically learns efficient, online, active visuomotor control of its eyes, head, and limbs in order to perform nontrivial tasks involving the foveation and visual pursuit of target objects coupled with visually-guided limb-reaching actions to intercept the moving targets, as well as to carry out drawing and writing tasks.

Exploiting the efficiency and stability of Position-Based Dynamics (PBD), we introduce a novel crowd simulation method that runs at interactive rates for hundreds of thousands of agents. Our method enables the detailed modeling of per-agent behavior in a Lagrangian formulation. We model short-range and long-range collision avoidance to simulate both sparse and dense crowds. On the particles representing agents, we formulate a set of positional constraints that can be readily integrated into a standard PBD solver. We augment the tentative particle motions with planning velocities to determine the preferred velocities of agents, and project the positions onto the constraint manifold to eliminate colliding configurations. The local short-range interaction is represented with collision and frictional contact between agents, as in the discrete simulation of granular materials. We incorporate a cohesion model for modeling collective behaviors and propose a new constraint for dealing with potential future collisions. Our new method is suitable for use in interactive games.