Conformal Symplectic Optimization for Stable Reinforcement Learning

Training deep reinforcement learning (RL) agents necessitates overcoming the highly unstable nonconvex stochastic optimization inherent in the trial-and-error mechanism. To tackle this challenge, we propose a physics-inspired optimization algorithm called relativistic adaptive gradient descent (RAD), which enhances long-term training stability. By conceptualizing neural network (NN) training as the evolution of a conformal Hamiltonian system, we present a universal framework for transferring long-term stability from conformal symplectic integrators to iterative NN updating rules, where the choice of kinetic energy governs the dynamical properties of resulting optimization algorithms. By utilizing relativistic kinetic energy, RAD incorporates principles from special relativity and limits parameter updates below a finite speed, effectively mitigating abnormal gradient influences. Additionally, RAD models NN optimization as the evolution of a multi-particle system where each trainable parameter acts as an independent particle with an individual adaptive learning rate. We prove RAD's sublinear convergence under general nonconvex settings, where smaller gradient variance and larger batch sizes contribute to tighter convergence. Notably, RAD degrades to the well-known adaptive moment estimation (ADAM) algorithm when its speed coefficient is chosen as one and symplectic factor as a small positive value. Experimental results show RAD outperforming nine baseline optimizers with five RL algorithms across twelve environments, including standard benchmarks and challenging scenarios. Notably, RAD achieves up to a 155.1% performance improvement over ADAM in Atari games, showcasing its efficacy in stabilizing and accelerating RL training.

Robust State Estimation for Legged Robots with Dual Beta Kalman Filter

Existing state estimation algorithms for legged robots that rely on proprioceptive sensors often overlook foot slippage and leg deformation in the physical world, leading to large estimation errors. To address this limitation, we propose a comprehensive measurement model that accounts for both foot slippage and variable leg length by analyzing the relative motion between foot contact points and the robot's body center. We show that leg length is an observable quantity, meaning that its value can be explicitly inferred by designing an auxiliary filter. To this end, we introduce a dual estimation framework that iteratively employs a parameter filter to estimate the leg length parameters and a state filter to estimate the robot's state. To prevent error accumulation in this iterative framework, we construct a partial measurement model for the parameter filter using the leg static equation. This approach ensures that leg length estimation relies solely on joint torques and foot contact forces, avoiding the influence of state estimation errors on the parameter estimation. Unlike leg length which can be directly estimated, foot slippage cannot be measured directly with the current sensor configuration. However, since foot slippage occurs at a low frequency, it can be treated as outliers in the measurement data. To mitigate the impact of these outliers, we propose the beta Kalman filter (beta KF), which redefines the estimation loss in canonical Kalman filtering using beta divergence. This divergence can assign low weights to outliers in an adaptive manner, thereby enhancing the robustness of the estimation algorithm. These techniques together form the dual beta-Kalman filter (Dual beta KF), a novel algorithm for robust state estimation in legged robots. Experimental results on the Unitree GO2 robot demonstrate that the Dual beta KF significantly outperforms state-of-the-art methods.

Hierarchical End-to-End Autonomous Driving: Integrating BEV Perception with Deep Reinforcement Learning

End-to-end autonomous driving offers a streamlined alternative to the traditional modular pipeline, integrating perception, prediction, and planning within a single framework. While Deep Reinforcement Learning (DRL) has recently gained traction in this domain, existing approaches often overlook the critical connection between feature extraction of DRL and perception. In this paper, we bridge this gap by mapping the DRL feature extraction network directly to the perception phase, enabling clearer interpretation through semantic segmentation. By leveraging Bird's-Eye-View (BEV) representations, we propose a novel DRL-based end-to-end driving framework that utilizes multi-sensor inputs to construct a unified three-dimensional understanding of the environment. This BEV-based system extracts and translates critical environmental features into high-level abstract states for DRL, facilitating more informed control. Extensive experimental evaluations demonstrate that our approach not only enhances interpretability but also significantly outperforms state-of-the-art methods in autonomous driving control tasks, reducing the collision rate by 20%.

Vision-Driven 2D Supervised Fine-Tuning Framework for Bird's Eye View Perception

Visual bird's eye view (BEV) perception, due to its excellent perceptual capabilities, is progressively replacing costly LiDAR-based perception systems, especially in the realm of urban intelligent driving. However, this type of perception still relies on LiDAR data to construct ground truth databases, a process that is both cumbersome and time-consuming. Moreover, most massproduced autonomous driving systems are only equipped with surround camera sensors and lack LiDAR data for precise annotation. To tackle this challenge, we propose a fine-tuning method for BEV perception network based on visual 2D semantic perception, aimed at enhancing the model's generalization capabilities in new scene data. Considering the maturity and development of 2D perception technologies, our method significantly reduces the dependency on high-cost BEV ground truths and shows promising industrial application prospects. Extensive experiments and comparative analyses conducted on the nuScenes and Waymo public datasets demonstrate the effectiveness of our proposed method.

Quantitative Representation of Scenario Difficulty for Autonomous Driving Based on Adversarial Policy Search

Adversarial scenario generation is crucial for autonomous driving testing because it can efficiently simulate various challenge and complex traffic conditions. However, it is difficult to control current existing methods to generate desired scenarios, such as the ones with different conflict levels. Therefore, this paper proposes a data-driven quantitative method to represent scenario difficulty. Compared with rule-based discrete scenario difficulty representation method, the proposed algorithm can achieve continuous difficulty representation. Specifically, the environment agent is introduced, and a reinforcement learning method combined with mechanism knowledge is constructed for policy search to obtain an agent with adversarial behavior. The model parameters of the environment agent at different stages in the training process are extracted to construct a policy group, and then the agents with different adversarial intensity are obtained, which are used to realize data generation in different difficulty scenarios through the simulation environment. Finally, a data-driven scenario difficulty quantitative representation model is constructed, which is used to output the environment agent policy under different difficulties. The result analysis shows that the proposed algorithm can generate reasonable and interpretable scenarios with high discrimination, and can provide quantifiable difficulty representation without any expert logic rule design. The video link is https://www.youtube.com/watch?v=GceGdqAm9Ys.

Rocket Landing Control with Random Annealing Jump Start Reinforcement Learning

Rocket recycling is a crucial pursuit in aerospace technology, aimed at reducing costs and environmental impact in space exploration. The primary focus centers on rocket landing control, involving the guidance of a nonlinear underactuated rocket with limited fuel in real-time. This challenging task prompts the application of reinforcement learning (RL), yet goal-oriented nature of the problem poses difficulties for standard RL algorithms due to the absence of intermediate reward signals. This paper, for the first time, significantly elevates the success rate of rocket landing control from 8% with a baseline controller to 97% on a high-fidelity rocket model using RL. Our approach, called Random Annealing Jump Start (RAJS), is tailored for real-world goal-oriented problems by leveraging prior feedback controllers as guide policy to facilitate environmental exploration and policy learning in RL. In each episode, the guide policy navigates the environment for the guide horizon, followed by the exploration policy taking charge to complete remaining steps. This jump-start strategy prunes exploration space, rendering the problem more tractable to RL algorithms. The guide horizon is sampled from a uniform distribution, with its upper bound annealing to zero based on performance metrics, mitigating distribution shift and mismatch issues in existing methods. Additional enhancements, including cascading jump start, refined reward and terminal condition, and action smoothness regulation, further improve policy performance and practical applicability. The proposed method is validated through extensive evaluation and Hardware-in-the-Loop testing, affirming the effectiveness, real-time feasibility, and smoothness of the proposed controller.

OE-BevSeg: An Object Informed and Environment Aware Multimodal Framework for Bird's-eye-view Vehicle Semantic Segmentation

Bird's-eye-view (BEV) semantic segmentation is becoming crucial in autonomous driving systems. It realizes ego-vehicle surrounding environment perception by projecting 2D multi-view images into 3D world space. Recently, BEV segmentation has made notable progress, attributed to better view transformation modules, larger image encoders, or more temporal information. However, there are still two issues: 1) a lack of effective understanding and enhancement of BEV space features, particularly in accurately capturing long-distance environmental features and 2) recognizing fine details of target objects. To address these issues, we propose OE-BevSeg, an end-to-end multimodal framework that enhances BEV segmentation performance through global environment-aware perception and local target object enhancement. OE-BevSeg employs an environment-aware BEV compressor. Based on prior knowledge about the main composition of the BEV surrounding environment varying with the increase of distance intervals, long-sequence global modeling is utilized to improve the model's understanding and perception of the environment. From the perspective of enriching target object information in segmentation results, we introduce the center-informed object enhancement module, using centerness information to supervise and guide the segmentation head, thereby enhancing segmentation performance from a local enhancement perspective. Additionally, we designed a multimodal fusion branch that integrates multi-view RGB image features with radar/LiDAR features, achieving significant performance improvements. Extensive experiments show that, whether in camera-only or multimodal fusion BEV segmentation tasks, our approach achieves state-of-the-art results by a large margin on the nuScenes dataset for vehicle segmentation, demonstrating superior applicability in the field of autonomous driving.

Risk-Aware Vehicle Trajectory Prediction Under Safety-Critical Scenarios

Trajectory prediction is significant for intelligent vehicles to achieve high-level autonomous driving, and a lot of relevant research achievements have been made recently. Despite the rapid development, most existing studies solely focused on normal safe scenarios while largely neglecting safety-critical scenarios, particularly those involving imminent collisions. This oversight may result in autonomous vehicles lacking the essential predictive ability in such situations, posing a significant threat to safety. To tackle these, this paper proposes a risk-aware trajectory prediction framework tailored to safety-critical scenarios. Leveraging distinctive hazardous features, we develop three core risk-aware components. First, we introduce a risk-incorporated scene encoder, which augments conventional encoders with quantitative risk information to achieve risk-aware encoding of hazardous scene contexts. Next, we incorporate endpoint-risk-combined intention queries as prediction priors in the decoder to ensure that the predicted multimodal trajectories cover both various spatial intentions and risk levels. Lastly, an auxiliary risk prediction task is implemented for the ultimate risk-aware prediction. Furthermore, to support model training and performance evaluation, we introduce a safety-critical trajectory prediction dataset and tailored evaluation metrics. We conduct comprehensive evaluations and compare our model with several SOTA models. Results demonstrate the superior performance of our model, with a significant improvement in most metrics. This prediction advancement enables autonomous vehicles to execute correct collision avoidance maneuvers under safety-critical scenarios, eventually enhancing road traffic safety.

Hierarchical and Decoupled BEV Perception Learning Framework for Autonomous Driving

Perception is essential for autonomous driving system. Recent approaches based on Bird's-eye-view (BEV) and deep learning have made significant progress. However, there exists challenging issues including lengthy development cycles, poor reusability, and complex sensor setups in perception algorithm development process. To tackle the above challenges, this paper proposes a novel hierarchical Bird's-eye-view (BEV) perception paradigm, aiming to provide a library of fundamental perception modules and user-friendly graphical interface, enabling swift construction of customized models. We conduct the Pretrain-Finetune strategy to effectively utilize large scale public datasets and streamline development processes. Specifically, we present a Multi-Module Learning (MML) approach, enhancing performance through synergistic and iterative training of multiple models. Extensive experimental results on the Nuscenes dataset demonstrate that our approach renders significant improvement over the traditional training method.

Convolutional Unscented Kalman Filter for Multi-Object Tracking with Outliers

Multi-object tracking (MOT) is an essential technique for navigation in autonomous driving. In tracking-by-detection systems, biases, false positives, and misses, which are referred to as outliers, are inevitable due to complex traffic scenarios. Recent tracking methods are based on filtering algorithms that overlook these outliers, leading to reduced tracking accuracy or even loss of the objects trajectory. To handle this challenge, we adopt a probabilistic perspective, regarding the generation of outliers as misspecification between the actual distribution of measurement data and the nominal measurement model used for filtering. We further demonstrate that, by designing a convolutional operation, we can mitigate this misspecification. Incorporating this operation into the widely used unscented Kalman filter (UKF) in commonly adopted tracking algorithms, we derive a variant of the UKF that is robust to outliers, called the convolutional UKF (ConvUKF). We show that ConvUKF maintains the Gaussian conjugate property, thus allowing for real-time tracking. We also prove that ConvUKF has a bounded tracking error in the presence of outliers, which implies robust stability. The experimental results on the KITTI and nuScenes datasets show improved accuracy compared to representative baseline algorithms for MOT tasks.