ENTROPY: Environment Transformer and Offline Policy Optimization

Model-based methods provide an effective approach to offline reinforcement learning (RL). They learn an environmental dynamics model from interaction experiences and then perform policy optimization based on the learned model. However, previous model-based offline RL methods lack long-term prediction capability, resulting in large errors when generating multi-step trajectories. We address this issue by developing a sequence modeling architecture, Environment Transformer, which can generate reliable long-horizon trajectories based on offline datasets. We then propose a novel model-based offline RL algorithm, ENTROPY, that learns the dynamics model and reward function by ENvironment TRansformer and performs Offline PolicY optimization. We evaluate the proposed method on MuJoCo continuous control RL environments. Results show that ENTROPY performs comparably or better than the state-of-the-art model-based and model-free offline RL methods and demonstrates more powerful long-term trajectory prediction capability compared to existing model-based offline methods.

Parallel Optimization for Cooperative Autonomous Driving at Unsignalized Roundabouts with Hard Safety Guarantees

The development of connected autonomous vehicles (CAVs) facilitates the enhancement of traffic efficiency in complicated scenarios. In unsignalized roundabout scenarios, difficulties remain unsolved in developing an effective and efficient coordination strategy for CAVs. In this paper, we formulate the cooperative autonomous driving problem of CAVs in the roundabout scenario as a constrained optimal control problem, and propose a computationally-efficient parallel optimization framework to generate strategies for CAVs such that the travel efficiency is improved with hard safety guarantees. All constraints involved in the roundabout scenario are addressed appropriately with convex approximation, such that the convexity property of the reformulated optimization problem is exhibited. Then, a parallel optimization algorithm is presented to solve the reformulated optimization problem, where an embodied iterative nearest neighbor search strategy to determine the optimal passing sequence in the roundabout scenario. It is noteworthy that the travel efficiency in the roundabout scenario is enhanced and the computation burden is considerably alleviated with the innovation development. We also examine the proposed method in CARLA simulator and perform thorough comparisons with a rule-based baseline and the commonly used IPOPT optimization solver to demonstrate the effectiveness and efficiency of the proposed approach.

Are All Point Clouds Suitable for Completion? Weakly Supervised Quality Evaluation Network for Point Cloud Completion

In the practical application of point cloud completion tasks, real data quality is usually much worse than the CAD datasets used for training. A small amount of noisy data will usually significantly impact the overall system's accuracy. In this paper, we propose a quality evaluation network to score the point clouds and help judge the quality of the point cloud before applying the completion model. We believe our scoring method can help researchers select more appropriate point clouds for subsequent completion and reconstruction and avoid manual parameter adjustment. Moreover, our evaluation model is fast and straightforward and can be directly inserted into any model's training or use process to facilitate the automatic selection and post-processing of point clouds. We propose a complete dataset construction and model evaluation method based on ShapeNet. We verify our network using detection and flow estimation tasks on KITTI, a real-world dataset for autonomous driving. The experimental results show that our model can effectively distinguish the quality of point clouds and help in practical tasks.

A Survey on Global LiDAR Localization

Knowledge about the own pose is key for all mobile robot applications. Thus pose estimation is part of the core functionalities of mobile robots. In the last two decades, LiDAR scanners have become a standard sensor for robot localization and mapping. This article surveys recent progress and advances in LiDAR-based global localization. We start with the problem formulation and explore the application scope. We then present the methodology review covering various global localization topics, such as maps, descriptor extraction, and consistency checks. The contents are organized under three themes. The first is the combination of global place retrieval and local pose estimation. Then the second theme is upgrading single-shot measurement to sequential ones for sequential global localization. The third theme is extending single-robot global localization to cross-robot localization on multi-robot systems. We end this survey with a discussion of open challenges and promising directions on global lidar localization.

Contour Context: Abstract Structural Distribution for 3D LiDAR Loop Detection and Metric Pose Estimation

This paper proposes \textit{Contour Context}, a simple, effective, and efficient topological loop closure detection pipeline with accurate 3-DoF metric pose estimation, targeting the urban utonomous driving scenario. We interpret the Cartesian birds' eye view (BEV) image projected from 3D LiDAR points as layered distribution of structures. To recover elevation information from BEVs, we slice them at different heights, and connected pixels at each level will form contours. Each contour is parameterized by abstract information, e.g., pixel count, center position, covariance, and mean height. The similarity of two BEVs is calculated in sequential discrete and continuous steps. The first step considers the geometric consensus of graph-like constellations formed by contours in particular localities. The second step models the majority of contours as a 2.5D Gaussian mixture model, which is used to calculate correlation and optimize relative transform in continuous space. A retrieval key is designed to accelerate the search of a database indexed by layered KD-trees. We validate the efficacy of our method by comparing it with recent works on public datasets.

Catch Planner: Catching High-Speed Targets in the Flight

Catching high-speed targets in the flight is a complex and typical highly dynamic task. In this paper, we propose Catch Planner, a planning-with-decision scheme for catching. For sequential decision making, we propose a policy search method based on deep reinforcement learning. In order to make catching adaptive and flexible, we propose a trajectory optimization method to jointly optimize the highly coupled catching time and terminal state while considering the dynamic feasibility and safety. We also propose a flexible constraint transcription method to catch targets at any reasonable attitude and terminal position bias. The proposed Catch Planner provides a new paradigm for the combination of learning and planning and is integrated on the quadrotor designed by ourselves, which runs at 100$hz$ on the onboard computer. Extensive experiments are carried out in real and simulated scenes to verify the robustness of the proposed method and its expansibility when facing a variety of high-speed flying targets.

PredRecon: A Prediction-boosted Planning Framework for Fast and High-quality Autonomous Aerial Reconstruction

Autonomous UAV path planning for 3D reconstruction has been actively studied in various applications for high-quality 3D models. However, most existing works have adopted explore-then-exploit, prior-based or exploration-based strategies, demonstrating inefficiency with repeated flight and low autonomy. In this paper, we propose PredRecon, a prediction-boosted planning framework that can autonomously generate paths for high 3D reconstruction quality. We obtain inspiration from humans can roughly infer the complete construction structure from partial observation. Hence, we devise a surface prediction module (SPM) to predict the coarse complete surfaces of the target from the current partial reconstruction. Then, the uncovered surfaces are produced by online volumetric mapping waiting for observation by UAV. Lastly, a hierarchical planner plans motions for 3D reconstruction, which sequentially finds efficient global coverage paths, plans local paths for maximizing the performance of Multi-View Stereo (MVS), and generates smooth trajectories for image-pose pairs acquisition. We conduct benchmarks in the realistic simulator, which validates the performance of PredRecon compared with the classical and state-of-the-art methods. The open-source code is released at https://github.com/HKUST-Aerial-Robotics/PredRecon.

The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition

Open-set Recognition (OSR) aims to identify test samples whose classes are not seen during the training process. Recently, Unified Open-set Recognition (UOSR) has been proposed to reject not only unknown samples but also known but wrongly classified samples, which tends to be more practical in real-world applications. The UOSR draws little attention since it is proposed, but we find sometimes it is even more practical than OSR in the real world applications, as evaluation results of known but wrongly classified samples are also wrong like unknown samples. In this paper, we deeply analyze the UOSR task under different training and evaluation settings to shed light on this promising research direction. For this purpose, we first evaluate the UOSR performance of several OSR methods and show a significant finding that the UOSR performance consistently surpasses the OSR performance by a large margin for the same method. We show that the reason lies in the known but wrongly classified samples, as their uncertainty distribution is extremely close to unknown samples rather than known and correctly classified samples. Second, we analyze how the two training settings of OSR (i.e., pre-training and outlier exposure) influence the UOSR. We find although they are both beneficial for distinguishing known and correctly classified samples from unknown samples, pre-training is also helpful for identifying known but wrongly classified samples while outlier exposure is not. In addition to different training settings, we also formulate a new evaluation setting for UOSR which is called few-shot UOSR, where only one or five samples per unknown class are available during evaluation to help identify unknown samples. We propose FS-KNNS for the few-shot UOSR to achieve state-of-the-art performance under all settings.

Decentralized iLQR for Cooperative Trajectory Planning of Connected Autonomous Vehicles via Dual Consensus ADMM

Developments in cooperative trajectory planning of connected autonomous vehicles (CAVs) have gathered considerable momentum and research attention. Generally, such problems present strong non-linearity and non-convexity, rendering great difficulties in finding the optimal solution. Existing methods typically suffer from low computational efficiency, and this hinders the appropriate applications in large-scale scenarios involving an increasing number of vehicles. To tackle this problem, we propose a novel decentralized iterative linear quadratic regulator (iLQR) algorithm by leveraging the dual consensus alternating direction method of multipliers (ADMM). First, the original non-convex optimization problem is reformulated into a series of convex optimization problems through iterative neighbourhood approximation. Then, the dual of each convex optimization problem is shown to have a consensus structure, which facilitates the use of consensus ADMM to solve for the dual solution in a fully decentralized and parallel architecture. Finally, the primal solution corresponding to the trajectory of each vehicle is recovered by solving a linear quadratic regulator (LQR) problem iteratively, and a novel trajectory update strategy is proposed to ensure the dynamic feasibility of vehicles. With the proposed development, the computation burden is significantly alleviated such that real-time performance is attainable. Two traffic scenarios are presented to validate the proposed algorithm, and thorough comparisons between our proposed method and baseline methods (including centralized iLQR, IPOPT, and SQP) are conducted to demonstrate the scalability of the proposed approach.

SemanticLoop: loop closure with 3D semantic graph matching

Loop closure can effectively correct the accumulated error in robot localization, which plays a critical role in the long-term navigation of the robot. Traditional appearance-based methods rely on local features and are prone to failure in ambiguous environments. On the other hand, object recognition can infer objects' category, pose, and extent. These objects can serve as stable semantic landmarks for viewpoint-independent and non-ambiguous loop closure. However, there is a critical object-level data association problem due to the lack of efficient and robust algorithms. We introduce a novel object-level data association algorithm, which incorporates IoU, instance-level embedding, and detection uncertainty, formulated as a linear assignment problem. Then, we model the objects as TSDF volumes and represent the environment as a 3D graph with semantics and topology. Next, we propose a graph matching-based loop detection based on the reconstructed 3D semantic graphs and correct the accumulated error by aligning the matched objects. Finally, we refine the object poses and camera trajectory in an object-level pose graph optimization. Experimental results show that the proposed object-level data association method significantly outperforms the commonly used nearest-neighbor method in accuracy. Our graph matching-based loop closure is more robust to environmental appearance changes than existing appearance-based methods.