Efficient BVH‐based Collision Detection Scheme with Ordering and Restructuring

Abstract

Bounding volume hierarchy (BVH) has been widely adopted as the acceleration structure in broad‐phase collision detection. Previous state‐of‐the‐art BVH‐based collision detection approaches exploited the spatio‐temporal coherence of simulations by maintaining a bounding volume test tree (BVTT) front. A major drawback of these algorithms is that large deformations in the scenes decrease culling efficiency and slow down collision queries. Moreover, for front‐based methods, the inefficient caching on GPU caused by the arbitrary layout of BVH and BVTT front nodes becomes a critical performance issue. We present a fast and robust BVH‐based collision detection scheme on GPU that addresses the above problems by ordering and restructuring BVHs and BVTT fronts. Our techniques are based on the use of histogram sort and an auxiliary structure BVTT front log, through which we analyze the dynamic status of BVTT front and BVH quality. Our approach efficiently handles inter‐ and intra‐object collisions and performs especially well in simulations where there is considerable spatio‐temporal coherence. The benchmark results demonstrate that our approach is significantly faster than the previous BVH‐based method, and also outperforms other state‐of‐the‐art spatial subdivision schemes in terms of speed.

Binary Ostensibly‐Implicit Trees for Fast Collision Detection

“…Wang et al . [WTMT18]). However, a degradation of BVH quality is also inevitable when accumulated deformations within dynamic scenes cause significant increases in the overlap among child bounding volumes.…”

“…[KIS∗12] propose a well‐related incremental update scheme by combining refitting with local restructuring to modify sub‐trees via rotations, and node splitting. However, they still advocate for a full rebuild when extreme degenerations occur, which has seen recent application within GPU‐based collision detection [WTMT18].…”

“…However, these approaches curb the memory problem heuristically, they are complex, and their success‐rate is not thoroughly investigated. A simpler approach is discussed in [WTMT18] which accounts for the order between BVH node pairs to cull up‐to 25% of redundant self‐collision tests, and is well suited for the implicit tree setting. Wang et al .…”

“…Wang et al . [WTMT18] present one of the fastest BVH‐based methods by ordering and restructuring the collision front and BVH, while using stackless depth‐first search (DFS) traversal. Their method proposes to use a histogram sort and auxiliary data structures to reduce random data access patterns arising from front updates, while providing a quality metric to mitigate BVH degradation.…”

Design and Application of Bounding Volume Hierarchy Collision Detection Algorithm Based on Virtual Sphere

“…Many researchers like Wei et al and Wang et al improved the BVH methods to achieve better collision detection performance, but these methods need large storage spaces. 8,9 Some methods, proposed by Müller et al and Zou et al, can only be used for collision detection of specific models, and have limitations in application. 10 Some methods, such as GPU-based collision detection algorithm designed by Tang et al and Weller et al, showed that its performance depends on the calculation speed of GPU.…”