DiffCo: Autodifferentiable Proxy Collision Detection With Multiclass Labels for Safety-Aware Trajectory Optimization

Zhi, Yuheng; Das, Nikhil; Yip, Michael C.

doi:10.1109/tro.2022.3153789

Cited by 18 publications

(11 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new kernel function is designed based on Fastron, which enhances the relationship between kinematics and configuration space and improves the accuracy of collision detection [31]. The DiffCo method is similar to Fastron in that obstacle manifold information is learned through a nonparametric kernel perceptron but it is mainly applied to optimization-based motion planners [32].…”

Section: Geometric Representationmentioning

confidence: 99%

Novel Probabilistic Collision Detection for Manipulator Motion Planning Using HNSW

Zhang,

Tao,

Jiang

et al. 2024

Machines

View full text Add to dashboard Cite

Collision detection is very important for robot motion planning. The existing accurate collision detection algorithms regard the evaluation of each node as a discrete event, ignoring the correlation between nodes, resulting in low efficiency. In this paper, we propose a novel approach that transforms collision detection into a binary classification problem. In particular, the proposed method searches the k-nearest neighbor (KNN) of the new node and estimates its collision probability by the prior node. We perform the hierarchical navigable small world (HNSW) method to query the nearest neighbor data and store the detected nodes to build the database incrementally. In addition, this research develops a KNN query technique tailored for linear data, incorporating threshold segmentation to facilitate collision detection along continuous paths. Moreover, it refines the distance function of the collision classifier to enhance the precision of probability estimations. Simulation results demonstrate the effectiveness of the proposed method.

show abstract

Section: Geometric Representationmentioning

confidence: 99%

Novel Probabilistic Collision Detection for Manipulator Motion Planning Using HNSW

Zhang,

Tao,

Jiang

et al. 2024

Machines

View full text Add to dashboard Cite

show abstract

“…Nevertheless, it has been shown that such geometric primitive approximations may lead to overlyconservative constraints that can interfere with the task or lead the robot to a collision, numerical instabilities and an increase in computational complexity as the number of obstacles increases; limiting their use for real-time reactive control [16], [17], [18]. To alleviate some of these issues, there has been a recent spike in works to account for collisions directly in the joint space of a robot [19], [20], [21]. This addresses some issues with kinematic-based collision detection, such as IK-caused singularities and local minima.…”

Section: Related Workmentioning

confidence: 99%

“…Notably, several works rely on active learning and online sampling to adjust the model learned for a static environment to a dynamic one [19]. It is further extended to use the gradients of the learned model in various path-planning pipelines [20]. However, even for a low-DoF manipulator, the reported update step (0.27 seconds) is too large to be used in real-time.…”

Section: Related Workmentioning

confidence: 99%

Neural Joint Space Implicit Signed Distance Functions for Reactive Robot Manipulator Control

Koptev

Figueroa

Billard

2023

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

“…Furthermore, the fact that it is analytically and efficiently evaluated is beneficial to the optimization procedure. We refer readers to Diffco [40] for an alterative still-differentiable SDF formulation that goes beyond spherical approximation for generality and is still computationally efficient for trajectory optimization.…”

Section: Objective Function and Safety Constraintsmentioning

confidence: 99%

Traffic-Aware Autonomous Driving with Differentiable Traffic Simulation

Zheng

Son

2023

2023 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Cloth manipulation is a category of deformable object manipulation of great interest to the robotics community, from applications of automated laundry-folding and home organizing and cleaning to textiles and flexible manufacturing. Despite the desire for automated cloth manipulation, the thinshell dynamics and under-actuation nature of cloth present significant challenges for robots to effectively interact with them. Many recent works omit explicit modeling in favor of learning-based methods that may yield control policies directly. However, these methods require large training sets that must be collected and curated. In this regard, we create a framework for differentiable modeling of cloth dynamics leveraging an Extended Position-based Dynamics (XPBD) algorithm. Together with the desired control objective, physics-aware regularization terms are designed for better results, including trajectory smoothness and elastic potential energy. In addition, safety constraints, such as avoiding obstacles, can be specified using signed distance functions (SDFs). We formulate the cloth manipulation task with safety constraints as a constrained optimization problem, which can be effectively solved by mainstream gradient-based optimizers thanks to the end-toend differentiability of our framework. Finally, we assess the proposed framework for manipulation tasks with various safety thresholds and demonstrate the feasibility of result trajectories on a surgical robot. The effects of the regularization terms are analyzed in an additional ablation study.

show abstract

DiffCo: Autodifferentiable Proxy Collision Detection With Multiclass Labels for Safety-Aware Trajectory Optimization

Cited by 18 publications

References 34 publications

Novel Probabilistic Collision Detection for Manipulator Motion Planning Using HNSW

Novel Probabilistic Collision Detection for Manipulator Motion Planning Using HNSW

Neural Joint Space Implicit Signed Distance Functions for Reactive Robot Manipulator Control

Traffic-Aware Autonomous Driving with Differentiable Traffic Simulation

Contact Info

Product

Resources

About