Efficient Configuration Space Construction and Optimization for Motion Planning

The configuration space is a fundamental conc ept that is widely used in algorithmic robotics. Many applications in robotics, computer-aided design, and related areas can be reduced to computational problems in terms of configuration spaces. In this paper, we survey some of our recent work on solving two important challenges related to configuration spaces:(1) how to efficiently compute an approximate representation of high-dimensional configuration spaces; and(2) how to efficiently perform geometric proximity and motion planning queries in high-dimensional configuration spaces. We present new configuration space construction algorithms based on machine learning and geometric approximation techniques. These algorithms perform collision queries on many configuration samples. The collision query results are used to compute an approximate representation for the configuration space, which quickly converges to the exact configuration space. We also present parallel GPU-based algorithms to accelerate the performance of optimization and search computations in configuration spaces. In particular, we design efficient GPU-based parallel k-nearest neighbor and parallel collision detection algorithms and use these algorithms to accelerate motion planning.

BADF:Bounding Volume Hierarchies Centric Adaptive Distance Field Computation for Deformable Objects on GPUs

We present a novel algorithm BADF(Bounding Volume Hierarchy Based Adaptive Distance Fields)for accelerating the construction of ADFs(adaptive distance fields)of rigid and deformable models on graphics processing units.Our approach is based on constructing a bounding volume hierarchy(BVH)and we use that hierarchy to generate an octree-based ADF.We exploit the coherence between successive frames and sort the grid points of the octree to accelerate the computation.Our approach is applicable to rigid and deformable models.Our GPU-based(graphics processing unit based)algorithm is about 20x--50x faster than current mainstream central processing unit based algorithms.Our BADF algorithm can construct the distance fields for deformable models with 60k triangles at interactive rates on an NVIDIA GTX GeForce 1060.Moreover,we observe 3x speedup over prior GPU-based ADF algorithms.

Editing smoke animation using a deforming grid

We present a new method for editing smoke animations by directly deforming the grid used for simulation. We present a modification to the widely used semi-Lagrangian advection operator and use it to transfer the deformation from the grid to the smoke body. Our modified operator bends the smoke particle streamlines according to the deformation gradient.We demonstrate that the controlled smoke animation preserves the fine-grained vortical velocity components and incompressibility constraints, while conforming to the deformed grid. Moreover, our approach enables interactive 3D smoke animation editing by using a reduced-dimensional subspace. Overall, our method makes it possible to use current mesh editing tools to control the smoke body.

Recurrent 3D attentional networks for end-to-end active object recognition

Active vision is inherently attention-driven:an agent actively selects views to attend in order to rapidly perform a vision task while improving its internal representation of the scene being observed.Inspired by the recent success of attention-based models in 2D vision tasks based on single RGB images, we address multi-view depth-based active object recognition using an attention mechanism, by use of an end-to-end recurrent 3D attentional network. The architecture takes advantage of a recurrent neural network to store and update an internal representation. Our model,trained with 3D shape datasets, is able to iteratively attend the best views targeting an object of interest for recognizing it. To realize 3D view selection, we derive a 3D spatial transformer network. It is dierentiable,allowing training with backpropagation, and so achieving much faster convergence than the reinforcement learning employed by most existing attention-based models. Experiments show that our method, with only depth input, achieves state-of-the-art next-best-view performance both in terms of time taken and recognition accuracy.