DiffCo: Auto-Differentiable Proxy Collision Detection with Multi-class Labels for Safety-Aware Trajectory Optimization

• URL: http://arxiv.org/abs/2102.07413v1
• Date: Mon, 15 Feb 2021 09:31:26 GMT
• Title: DiffCo: Auto-Differentiable Proxy Collision Detection with Multi-class Labels for Safety-Aware Trajectory Optimization
• Authors: Yuheng Zhi, Nikhil Das, Michael Yip
• Abstract summary: We present DiffCo, the first, fully auto-differentiable, non-parametric model for collision detection. It provides robust gradients for trajectory optimization via backpropagation and is often 10-100x faster to compute than its geometric counterparts.
• Score: 5.35056843248536
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The objective of trajectory optimization algorithms is to achieve an optimal collision-free path between a start and goal state. In real-world scenarios where environments can be complex and non-homogeneous, a robot needs to be able to gauge whether a state will be in collision with various objects in order to meet some safety metrics. The collision detector should be computationally efficient and, ideally, analytically differentiable to facilitate stable and rapid gradient descent during optimization. However, methods today lack an elegant approach to detect collision differentiably, relying rather on numerical gradients that can be unstable. We present DiffCo, the first, fully auto-differentiable, non-parametric model for collision detection. Its non-parametric behavior allows one to compute collision boundaries on-the-fly and update them, requiring no pre-training and allowing it to update continuously in dynamic environments. It provides robust gradients for trajectory optimization via backpropagation and is often 10-100x faster to compute than its geometric counterparts. DiffCo also extends trivially to modeling different object collision classes for semantically informed trajectory optimization.

Related papers

• Autonomous Vehicle Controllers From End-to-End Differentiable Simulation [60.05963742334746]
  We propose a differentiable simulator and design an analytic policy gradients (APG) approach to training AV controllers. Our proposed framework brings the differentiable simulator into an end-to-end training loop, where gradients of environment dynamics serve as a useful prior to help the agent learn a more grounded policy. We find significant improvements in performance and robustness to noise in the dynamics, as well as overall more intuitive human-like handling.
  arXiv  Detail & Related papers  (2024-09-12T11:50:06Z)
• Event-Aided Time-to-Collision Estimation for Autonomous Driving [28.13397992839372]
  We present a novel method that estimates the time to collision using a neuromorphic event-based camera. The proposed algorithm consists of a two-step approach for efficient and accurate geometric model fitting on event data. Experiments on both synthetic and real data demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2024-07-10T02:37:36Z)
• Distance and Collision Probability Estimation from Gaussian Surface Models [0.9208007322096533]
  Continuous-space collision probability estimation is critical for uncertainty-aware motion planning. Most collision detection and avoidance approaches assume the robot is modeled as a sphere, but ellipsoidal representations provide tighter approximations. State-of-the-art methods derive the Euclidean distance and gradient by processing raw point clouds.
  arXiv  Detail & Related papers  (2024-01-31T21:28:40Z)
• Unbalanced Optimal Transport: A Unified Framework for Object Detection [97.74382560746987]
  We show how Unbalanced Optimal Transport unifies different approaches to object detection. We show that training an object detection model with Unbalanced Optimal Transport is able to reach the state-of-the-art. The approach is well suited for GPU implementation, which proves to be an advantage for large-scale models.
  arXiv  Detail & Related papers  (2023-07-05T16:21:52Z)
• Accelerated First-Order Optimization under Nonlinear Constraints [73.2273449996098]
  We exploit between first-order algorithms for constrained optimization and non-smooth systems to design a new class of accelerated first-order algorithms. An important property of these algorithms is that constraints are expressed in terms of velocities instead of sparse variables.
  arXiv  Detail & Related papers  (2023-02-01T08:50:48Z)
• Particle-Based Score Estimation for State Space Model Learning in Autonomous Driving [62.053071723903834]
  Multi-object state estimation is a fundamental problem for robotic applications. We consider learning maximum-likelihood parameters using particle methods. We apply our method to real data collected from autonomous vehicles.
  arXiv  Detail & Related papers  (2022-12-14T01:21:05Z)
• Obstacle Identification and Ellipsoidal Decomposition for Fast Motion Planning in Unknown Dynamic Environments [0.0]
  Collision avoidance in unknown environments is one of the most critical challenges for unmanned systems. We present a method that identifies obstacles in terms of ellipsoids to estimate linear and angular obstacle velocities.
  arXiv  Detail & Related papers  (2022-09-28T17:00:10Z)
• Exact and Bounded Collision Probability for Motion Planning under Gaussian Uncertainty [1.3535770763481902]
  We present an approach for computing the collision probability under Gaussian distributed motion. The collision condition is formulated as the distance between ellipsoids. We provide a tight upper bound that can be computed much faster during online planning.
  arXiv  Detail & Related papers  (2021-10-12T20:45:18Z)
• An Integrated Localisation, Motion Planning and Obstacle Avoidance Algorithm in Belief Space [1.3535770763481902]
  Noisy sensors and actuation errors compound to the errors introduced while estimating features of the environment. We present a novel approach to incorporate these uncertainties for robot state estimation. We compute the probability of collision pertaining to the estimated robot configurations.
  arXiv  Detail & Related papers  (2021-01-27T17:47:45Z)
• DiffPD: Differentiable Projective Dynamics with Contact [65.88720481593118]
  We present DiffPD, an efficient differentiable soft-body simulator with implicit time integration. We evaluate the performance of DiffPD and observe a speedup of 4-19 times compared to the standard Newton's method in various applications.
  arXiv  Detail & Related papers  (2021-01-15T00:13:33Z)
• Scalable Differentiable Physics for Learning and Control [99.4302215142673]
  Differentiable physics is a powerful approach to learning and control problems that involve physical objects and environments. We develop a scalable framework for differentiable physics that can support a large number of objects and their interactions.
  arXiv  Detail & Related papers  (2020-07-04T19:07:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.