Trajectory Planning for Autonomous Vehicle Using Iterative Reward Prediction in Reinforcement Learning

Traditional trajectory planning methods for autonomous vehicles have several limitations. Heuristic and explicit simple rules make trajectory lack generality and complex motion. One of the approaches to resolve the above limitations of traditional trajectory planning methods is trajectory planning using reinforcement learning. However, reinforcement learning suffers from instability of learning and prior works of trajectory planning using reinforcement learning didn't consider the uncertainties. In this paper, we propose a trajectory planning method for autonomous vehicles using reinforcement learning. The proposed method includes iterative reward prediction method that stabilizes the learning process, and uncertainty propagation method that makes the reinforcement learning agent to be aware of the uncertainties. The proposed method is experimented in the CARLA simulator. Compared to the baseline method, we have reduced the collision rate by 60.17%, and increased the average reward to 30.82 times.

Safe and Efficient Trajectory Optimization for Autonomous Vehicles using B-spline with Incremental Path Flattening

B-spline-based trajectory optimization has been widely used in robot navigation, especially as quadrotor-like vehicles can easily enjoy the advantage of a B-spline curve (e.g. computational efficiency) with its convex hull property for trajectory optimization. Nevertheless, leveraging the B-splined-based optimization algorithm to generate a collision-free trajectory for autonomous vehicles is still challenging because their complex vehicle kinematics make it difficult to use the convex hull property. In this paper, we propose a novel trajectory optimization algorithm for autonomous vehicles that enables the advantage of a B-spline curve into a B-spline-based optimization algorithm by incorporating vehicle kinematics with two methods. An incremental path flattening is a new method that iteratively increases path curvature weight around vehicle collision points to find a collision-free path by reducing swept volume. A new swept volume estimation method can reduce over-approximation of the swept volume and make the vehicle pass through a narrow corridor without losing safety. Furthermore, a clamped B-spline curvature constraint, which can simplify a B-spline curvature constraint, is added with other feasibility constraints (e.g. longitudinal \& lateral velocity and acceleration) for the vehicle kinodynamic constraints. Our experimental results demonstrate that our method outperforms state-of-the-art baselines in various simulated environments and verifies its valid tracking performance with an autonomous vehicle in a real-world scenario.

Occlusion-aware Risk Assessment and Driving Strategy for Autonomous Vehicles Using Simplified Reachability Quantification

There are several unresolved challenges for autonomous vehicles. One of them is safely navigating among occluded pedestrians and vehicles. Much of the previous work tried to solve this problem by generating phantom cars and assessing their risk. In this paper, motivated by the previous works, we propose an algorithm that efficiently assesses risks of phantom pedestrians/vehicles using Simplified Reachability Quantification. We utilized this occlusion risk to set a speed limit at the risky position when planning the velocity profile of an autonomous vehicle. This allows an autonomous vehicle to safely and efficiently drive in occluded areas. The proposed algorithm was evaluated in various scenarios in the CARLA simulator and it reduced the average collision rate by 6.14X, the discomfort score by 5.03X, while traversal time was increased by 1.48X compared to baseline 1, and computation time was reduced by 20.15X compared to baseline 2.

Sampling is Matter: Point-guided 3D Human Mesh Reconstruction

This paper presents a simple yet powerful method for 3D human mesh reconstruction from a single RGB image. Most recently, the non-local interactions of the whole mesh vertices have been effectively estimated in the transformer while the relationship between body parts also has begun to be handled via the graph model. Even though those approaches have shown the remarkable progress in 3D human mesh reconstruction, it is still difficult to directly infer the relationship between features, which are encoded from the 2D input image, and 3D coordinates of each vertex. To resolve this problem, we propose to design a simple feature sampling scheme. The key idea is to sample features in the embedded space by following the guide of points, which are estimated as projection results of 3D mesh vertices (i.e., ground truth). This helps the model to concentrate more on vertex-relevant features in the 2D space, thus leading to the reconstruction of the natural human pose. Furthermore, we apply progressive attention masking to precisely estimate local interactions between vertices even under severe occlusions. Experimental results on benchmark datasets show that the proposed method efficiently improves the performance of 3D human mesh reconstruction. The code and model are publicly available at: https://github.com/DCVL-3D/PointHMR_release.

Structured Consistency Loss for semi-supervised semantic segmentation

The consistency loss has played a key role in solving problems in recent studies on semi-supervised learning. Yet extant studies with the consistency loss are limited to its application to classification tasks; extant studies on semi-supervised semantic segmentation rely on pixel-wise classification, which does not reflect the structured nature of characteristics in prediction. We propose a structured consistency loss to address this limitation of extant studies. Structured consistency loss promotes consistency in inter-pixel similarity between teacher and student networks. Specifically, collaboration with CutMix optimizes the efficient performance of semi-supervised semantic segmentation with structured consistency loss by reducing computational burden dramatically. The superiority of proposed method is verified with the Cityscapes; The Cityscapes benchmark results with validation and with test data are 81.9 mIoU and 83.84 mIoU respectively. This ranks the first place on the pixel-level semantic labeling task of Cityscapes benchmark suite. To the best of our knowledge, we are the first to present the superiority of state-of-the-art semi-supervised learning in semantic segmentation.