Fixed-Lag smoothing is widely employed as a backend in localization tasks. Generally, increasing the window length leads to better accuracy, but demands more computational resources. Therefore, determining an appropriate window length and whether a fixed length should be maintained throughout the localization process are worth studying. Assuming independent and identically distributed noise based on the distance-independent characteristic of LiDAR ranging errors, we propose an uncertainty-based adaptive sliding window (ASW) strategy. Through mathematical derivation, the reference uncertainty is affected by the LiDAR feature distribution of each frame. Consequently, we develop a multimodal LiDAR inertial odometry and mapping framework based on ASW, which integrates mechanical and solid-state LiDAR to enhance odometry accuracy and mapping density. By designing a joint matching module, our approach leverages the strengths of distinct scanning patterns. Additionally, we incorporate loop closure detection in the mapping process to minimize cumulative drift. Extensive experiments conducted on both public and self-collected datasets demonstrate the effectiveness of our method. Compared to the state-of-the-art method, our approach improves the average accuracy by 10.3%. We also provide an open-source implementation for further studies. https://github.com/wowhhhhgd/ASW-LIOM.

Keypoint detection and description are fundamental tasks for a variety of computer vision applications. Due to the limited receptive field of convolutional neural networks, most existing methods based on deep learning mainly focus on the local features, instead of taking into account the global context from entire image. The purpose of this work is to enhance the detection and description process of keypoints by leveraging global information obtained from Transformer, and to boost the consistence between keypoints and descriptors through their interaction. Specifically, the above two improvements are respectively implemented through the Local & Global Context Aggregation (LGCA) Module and Point & Descriptor Cross Augmentation (PDCA) Module proposed in this article. The LGCA module, which can model the long-range context, is inserted a Feature Pyramid Network (FPN) to extract features which contain diverse scales and different receptive fields. Moreover, the PDCA module enhances descriptors by the geometry information of keypoints detected, while enhancing the keypoint detection process by the position coordinates of correctly matched descriptors. Finally, we design a lightweight model to improve the running efficiency. Extensive experiments on various tasks demonstrate that our method achieves a substantial performance improvement over the current feature extraction methods. Code is available at: https://github.com/meng152634/CA2Point.

The suspension system, through effective damping of vibrations and shocks, can enhance the stability of wheeled robots traversing challenging terrain. Because the suspension system decouples the rigid correspondence between terrain changes and robot vibrations, considering suspension modeling in trajectory planning offers the advantage of more accurate prediction of the robot’s response to terrain. This improved predictive capability facilitates the planning of safer trajectories and may reduce tracking errors in the subsequent control process. In this work, inspired by the structure of Physics-Informed Neural Network (PINN), we propose a physics-informed planning method that considers the vibrational effects of complex nonlinear suspension systems. In addition, we design a two-stage process to accelerate training. By incorporating PINN, our method can better guarantee the physical feasibility of the planned trajectories. The proposed approach has been evaluated on a real robot platform. Compared to state-of-the-art baseline methods, our proposed approach achieves a 15.38% reduction in hazardous planning for mobile robots in wild environments.

High-definition (HD) maps are essential for autonomous driving, providing detailed and accurate environmental information. Recent advancements in online vectorized HD map construction have shown great promise, particularly methods that leverage existing maps as prior knowledge to improve performance. However, the robustness of these prior-enhanced methods under varying deviations between the priors and the real world remains a critical concern. This paper introduces a novel framework for generating synthetic maps, which allows for the controllable magnitude of diverse deviations, including geometric distortions, topological errors, and semantic inconsistencies, simulating real-world scenarios where prior maps may be outdated or inaccurate. Furthermore, lane group constraints are designed to avoid positional conflicts when map elements are modified. The synthesis method can overcome the time-consuming challenge of collecting real road changes. We demonstrate the utility of the synthetic deviation maps by incorporating them into the state-of-the-art prior-enhanced construction methods. The results reveal how different types and degrees of deviations affect the prediction accuracy, providing worthwhile insights into their robustness. Overall, this work contributes to a data augmentation and provides a valuable tool for developing more robust and reliable autonomous driving systems. The code is opensource and available at https://github.com/healenrens/Syn-D-maps.

In wild environments, motion planning for mobile robots faces the challenge of local optimal path traps due to limited sensor perception range and lack of spatial awareness. Existing approaches that avoid local optimum by designing heuristic functions or high-quality global paths in wild environments are time-consuming and unstable. This work proposes F3DMP, which consists of two parts to alleviate the local optimum solution and better utilize distant terrain information. First, the entire planning framework is adapted to the three-dimensional space so that the planning result conforms to the geometric characteristics of the terrain. Second, a time allocation function based on offline reinforcement learning is proposed. This function can anticipate potential challenges or opportunities based on semantic information for the image and proactively determine a time allocation. Our planner is integrated into a complete mobile robot system and deployed to a real robot. Experiments in simulation and the real world demonstrate that our method can improve the success rate by 28% and the trajectory smoothness by 27% compared with traditional methods.

In unstructured environments with complex obstacles and obscure road boundaries, the local planner faces more severe challenges in terms of safety and real-time performance. In order to fulfill these emerging requirements, we propose a novel Timed-Elastic-Band approach for unstructured environments, abbreviated as TEB-U. This approach incorporates a free space extraction optimization module for 2D occupancy grid maps, which efficiently transforms irregular free space boundaries into polygons and restrains robots within the boundaries. Moreover, a dynamic global point adjustment module is designed to adaptively correct the trajectory points obtained from the global planner, thereby enabling robots to travel along the centerline of free space and providing a better initial trajectory for subsequent modules. To reduce the computational cost, we replace the obstacle constraint of TEB with the boundary constraint in hyper-graph optimization. We evaluate our planner in three distinct scenarios, and the results show that TEB-U improves the average success rate by 21% and reduces the planning time by 23% compared to TEB in unstructured road, which demonstrates its safety and efficiency.

Trajectory planning is important for ground robots to achieve safe and efficient autonomous navigation in unstructured off-road environments. Most existing methods treat each terrain as a single type. However, in the real world, a ground usually consists of hybrid terrains. In this work, we propose a novel trajectory planning network that handles hybrid terrain. To further enhance safety, we have designed a self-correcting structure based on historical planning data. This structure can correct the trajectory when an inappropriate one is planned. To train the network, we introduce a two-stage training scheme based on Offline Meta-Reinforcement Learning, which can train the network with pre-collected non-optimal datasets and reduce the occurrence of hazardous planning. The proposed approach has been evaluated on both simulated datasets and a real robot platform. Compared to state-of-the-art baseline methods, the proposed approach reduces hazardous planning by 59.3% in hybrid terrains.

Among the various driving situations, there are challenging road conditions where both the texture and curvature are variables over time (e.g., mountainous area). However, it is found that the characteristics of road texture and curvature have been respectively considered in some of the existing studies to determine the vehicle speed for trajectory planning, but the complementary effect of these two factors is still yet to be incorporated. This could lead to unsafe vehicle behaviour. This limitation has led us to develop a trajectory planning method that gives a systematic consideration of road conditions and leverages the complementary effect of road curvature and adhesion on the vehicle speed. It prioritises the trajectory safety through a preview of road constraints (i.e., waypoints, curvature and adhesion) in a look-ahead distance and the real-time computation of the vehicle speed that satisfies the constraints. In the experiment, our method was compared with the state-of-the-art techniques in a simulated mountainous driving environment, namely Model Predictive Control (MPC), Deep Reinforcement Learning (DRL) and Hybrid A*. The environment was built with abundant variation in road curvature and adhesion. The results showed that our approach was able to generate safe and comfort trajectories in both sharp turn and ice-covered driving scenarios, in which the vehicle successfully passed through the whole length of the global path without producing large deviations and exceeding lane boundaries. Whereas, the MPC, DRL and Hybrid A* approaches resulted in the vehicle exceeding lanes at some point with completeness levels of 77.72%, 75.31% and 79.53%, respectively.

We present AVS-HRL, a modular Active visual SLAM system based on hierarchical reinforcement learning. The reward function explicitly considers the efficiency of exploration and the accuracy of mapping by utilizing the internal variables of SLAM, such as feature points distribution and loop-closure signal. Compared to end-to-end active SLAM methods, we designed a map reconstruction module that can correct the cumulative error in the incremental mapping process. Furthermore, the inputs of all neural network modules use more abstract and general information, such as grid maps, rather than raw sensor observations. We conducted experiments in two different simulators and real-world environments. In the noisy setting of Habitat environments, our method improves the accuracy of the mapped areas by 68.48% as an average of Gibson and MP3D datasets. Moreover, our method's generalization performance was demonstrated through direct transfer across different simulators and real-world environments.

How to take into account both the calculation cost and positioning accuracy when driving over a long distance in the scene of changing satellite visibility, such as urban areas and mountain roads, is a research topic worth of attention for intelligent vehicles. In this paper, a tightly-coupled RTK/INS positioning algorithm base on adaptive lag smoother is proposed. By combining the uncertainty of the state to be estimated at the current time and the quantitative score of satellite visibility, the lag-length in smoother can be adjusted adaptively, so as to ensure positioning accuracy while reducing the calculation cost of marginal benefit consumption as much as possible. The proposed algorithm is demonstrated in both the simulator and real-world urban roads. From the experimental results, it is found that the estimation accuracy achieved by the adaptive lag smoother is similar to that of smoothers with long lag length, but the time consumption is reduced by about 30%. Under the same condition that the positioning can be completed in real time, the accuracy of the algorithm in this paper is 27% higher than that of the tightly-coupled RTK/INS system based on extended Kalman filter.

Generalizing policies across different domains with dynamics mismatch poses a significant challenge in reinforcement learning. For example, a robot learns the policy in a simulator, but when it is deployed in the real world, the dynamics of the environment may be different. Given the source and target domain with dynamics mismatch, we consider the online dynamics adaptation problem, in which case the agent can access sufficient source domain data while online interactions with the target domain are limited. Existing research has attempted to solve the problem from the dynamics discrepancy perspective. In this work, we reveal the limitations of these methods and explore the problem from the value difference perspective via a novel insight on the value consistency across domains. Specifically, we present the Value-Guided Data Filtering (VGDF) algorithm, which selectively shares transitions from the source domain based on the proximity of paired value targets across the two domains. Empirical results on various environments with kinematic and morphology shifts demonstrate that our method achieves superior performance compared to prior approaches.

Autonomous racing has lately gained popularity because of its entertainment value and potential of advancing autonomous driving in high-speed situations. These high-speed racing efforts usually focus on a road domain with fixed dynamics. They cannot meet the challenge of policy adaptation between domains with large dynamics gaps. Meanwhile, existing policy adaptation methods either rely on experts to build new environments for policy training, or only handle a small dynamics gap for low-speed control tasks due to limited dynamics modeling and rigorous data collection assumptions. To overcome these drawbacks, we introduce DAARL, a novel policy adaptation algorithm that uses adversarial and reinforcement learning to bridge the large dynamics gap between different domains. It has two training stages. In the first training stage, a domain transfer function is learned by adversarial learning to better capture the dynamics gap. The single domain transfer function integrates with the source domain to implement the dynamics of different target domains virtually without the help of experts. We name these virtual domains the imaginary target domains. In the second training stage, the knowledge of the source-domain policy guides the reinforcement learning of a target-domain policy on an imaginary target domain. It improves the convergence of the target-domain policy. Five experiments have been conducted on a racing simulator with different road domains. All results show that DAARL outperforms baselines in terms of driving speed, stability, success rate, and domain scalability.

Model predictive control is a promising method in robot control tasks. How to design an effective model structure and efficient prediction framework for model predictive control is still an open challenge. To reduce the time consumption and avoid compounding-error of the multi-step prediction process in model predictive control, we propose a single-model simultaneous framework, which uses single dynamics model to predict the entire prediction horizon simultaneously by taking all control actions with the current state as inputs. Based on this framework, we further propose an adversarial dynamics model that contains two parts. The generator provides a dynamics model for the prediction process, while the discriminator provides constraints that are hard to describe by manually defined loss. This adversarial dynamics model can accelerate training and improve model accuracy in unstructured environments. Experiments conducted in Gazebo simulator and on a real mobile robot demonstrate the efficiency and accuracy of the single-model simultaneous framework with an adversarial dynamics model.

Feature-based lidar odometry methods have attracted increasing attention due to their low computational cost. However, theoretically analysis of the effect of extracted features on pose estimation is still lacked. In this paper, we propose a method of key-feature selection for lightweight lidar inertial odometry, KFS-LIO, to further enhance the real-time performance by selecting the most effective subset of lidar feature constraints. Aiming at explaining the correlation between the feature distribution and state errors, a quantitative evaluation method of lidar constraints is introduced. In addition, to avoid recalculating the reprojection matrices in de-skewing step, we use the intermediate variables in IMU preintegration to compensate for lidar motion distortion. The experimental results demonstrate that KFS-LIO can reduce half of the LOAM features and provide comparable accuracy with the state-of-the-art odometry.