Jorge Ocampo Jimenez

Jorge Ocampo Jimenez, Wael Suleiman

This paper presents a novel method for accelerating path planning tasks in unknown scenes with obstacles by utilizing Wasserstein Generative Adversarial Networks (WGANs) with Gradient Penalty (GP) to approximate the distribution of the free conditioned configuration space. Our proposed approach involves conditioning the WGAN-GP with a Variational Auto-Encoder in a continuous latent space to handle multimodal datasets. However, training a Variational Auto-Encoder with WGAN-GP can be challenging for image-to-configuration-space problems, as the Kullback-Leibler loss function often converges to a random distribution. To overcome this issue, we simplify the configuration space as a set of Gaussian distributions and divide the dataset into several local models. This enables us to not only learn the model but also speed up its convergence. We evaluate the reconstructed configuration space using the homology rank of manifolds for datasets with the geometry score. Furthermore, we propose a novel transformation of the robot's configuration space that enables us to measure how well collision-free regions are reconstructed, which could be used with other rank of homology metrics. Our experiments show promising results for accelerating path planning tasks in unknown scenes while generating quasi-optimal paths with our WGAN-GP. The source code is openly available.

Jorge Ocampo Jimenez, Wael Suleiman

The representation of a Configuration Space C plays a vital role in accelerating the finding of a collision-free path for sampling-based motion planners where the majority of computation time is spent in collision checking of states. Traditionally, planners evaluate C's representations through limited evaluations of collision-free paths using the collision checker or by reducing the dimensionality of C for visualization. However, a collision checker may indicate high accuracy even when only a subset of the original C is represented; limiting the motion planner's ability to find paths comparable to those in the original C. Additionally, dealing with high-dimensional Cs is challenging, as qualitative evaluations become increasingly difficult in dimensions higher than three, where reduced-dimensional C evaluation may decrease accuracy in cluttered environments. In this paper, we present a novel approach for visualizing representations of high-dimensional Cs of manipulator robots in a 2D format. We provide a new tool for qualitative evaluation of high-dimensional Cs approximations without reducing the original dimension. This enhances our ability to compare the accuracy and coverage of two different high-dimensional Cs. Leveraging the kinematic chain of manipulator robots and human color perception, we show the efficacy of our method using a 7-degree-of-freedom CS of a manipulator robot. This visualization offers qualitative insights into the joint boundaries of the robot and the coverage of collision state combinations without reducing the dimensionality of the original data. To support our claim, we conduct a numerical evaluation of the proposed visualization.

Jorge Ocampo Jimenez, Wael Suleiman

This paper presents a novel method for accelerating path-planning tasks in unknown scenes with obstacles by utilizing Wasserstein Generative Adversarial Networks (WGANs) with Gradient Penalty (GP) to approximate the distribution of waypoints for a collision-free path using the Rapidly-exploring Random Tree algorithm. Our approach involves conditioning the WGAN-GP with a forward diffusion process in a continuous latent space to handle multimodal datasets effectively. We also propose encoding the waypoints of a collision-free path as a matrix, where the multidimensional ordering of the waypoints is naturally preserved. This method not only improves model learning but also enhances training convergence. Furthermore, we propose a method to assess whether the trained model fails to accurately capture the true waypoints. In such cases, we revert to uniform sampling to ensure the algorithm's probabilistic completeness; a process that traditionally involves manually determining an optimal ratio for each scenario in other machine learning-based methods. Our experiments demonstrate promising results in accelerating path-planning tasks under critical time constraints. The source code is openly available at https://bitbucket.org/joro3001/imagewgangpplanning/src/master/.