arXiv subjects

Chen Lv

Publications and source records attributed to Chen Lv.

At least 73 records · Page 4Linked to original sources

arXiv2025

Complementary Learning System Empowers Online Continual Learning of Vehicle Motion Forecasting in Smart Cities

Artificial intelligence underpins most smart city services, yet deep neural network (DNN) that forecasts vehicle motion still struggle with catastrophic forgetting, the loss of earlier knowledge when models are updated. Conventional fixes enlarge the training set or replay past data, but these strategies incur high data collection costs, sample inefficiently and fail to balance long- and short-term experience, leaving them short of human-like continual learning. Here we introduce Dual-LS, a task-free, online continual learning paradigm for DNN-based motion forecasting that is inspired by the complementary learning system of the human brain. Dual-LS pairs two synergistic memory rehearsal replay mechanisms to accelerate experience retrieval while dynamically coordinating long-term and short-term knowledge representations. Tests on naturalistic data spanning three countries, over 772,000 vehicles and cumulative testing mileage of 11,187 km show that Dual-LS mitigates catastrophic forgetting by up to 74.31\% and reduces computational resource demand by up to 94.02\%, markedly boosting predictive stability in vehicle motion forecasting without inflating data requirements. Meanwhile, it endows DNN-based vehicle motion forecasting with computation efficient and human-like continual learning adaptability fit for smart cities.

cs.LG↗

arXiv2025

POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction

3D reconstruction in dynamic scenes primarily relies on the combination of geometry estimation and matching modules where the latter task is pivotal for distinguishing dynamic regions which can help to mitigate the interference introduced by camera and object motion. Furthermore, the matching module explicitly models object motion, enabling the tracking of specific targets and advancing motion understanding in complex scenarios. Recently, the proposed representation of pointmap in DUSt3R suggests a potential solution to unify both geometry estimation and matching in 3D space, but it still struggles with ambiguous matching in dynamic regions, which may hamper further improvement. In this work, we present POMATO, a unified framework for dynamic 3D reconstruction by marrying pointmap matching with temporal motion. Specifically, our method first learns an explicit matching relationship by mapping RGB pixels from both dynamic and static regions across different views to 3D pointmaps within a unified coordinate system. Furthermore, we introduce a temporal motion module for dynamic motions that ensures scale consistency across different frames and enhances performance in tasks requiring both precise geometry and reliable matching, most notably 3D point tracking. We show the effectiveness of the proposed pointmap matching and temporal fusion paradigm by demonstrating the remarkable performance across multiple downstream tasks, including video depth estimation, 3D point tracking, and pose estimation. Code and models are publicly available at https://github.com/wyddmw/POMATO.

eess.IV↗

arXiv2025

Recasting Classical Motion Planning for Contact-Rich Manipulation

In this work, we explore how conventional motion planning algorithms can be reapplied to contact-rich manipulation tasks. Rather than focusing solely on efficiency, we investigate how manipulation aspects can be recast in terms of conventional motion-planning algorithms. Conventional motion planners, such as Rapidly-Exploring Random Trees (RRT), typically compute collision-free paths in configuration space. However, in many manipulation tasks, contact is either unavoidable or essential for task success, such as for creating space or maintaining physical equilibrium. As such, we presents Haptic Rapidly-Exploring Random Trees (HapticRRT), a planning algorithm that incorporates a recently proposed optimality measure in the context of \textit{quasi-static} manipulation, based on the (squared) Hessian of manipulation potential. The key contributions are i) adapting classical RRT to operate on the quasi-static equilibrium manifold, while deepening the interpretation of haptic obstacles and metrics; ii) discovering multiple manipulation strategies, corresponding to branches of the equilibrium manifold. iii) validating the generality of our method across three diverse manipulation tasks, each requiring only a single manipulation potential expression. The video can be found at https://youtu.be/R8aBCnCCL40.

cs.RO↗

arXiv2025

Self-supervised Pretraining for Integrated Prediction and Planning of Automated Vehicles

Predicting the future of surrounding agents and accordingly planning a safe, goal-directed trajectory are crucial for automated vehicles. Current methods typically rely on imitation learning to optimize metrics against the ground truth, often overlooking how scene understanding could enable more holistic trajectories. In this paper, we propose Plan-MAE, a unified pretraining framework for prediction and planning that capitalizes on masked autoencoders. Plan-MAE fuses critical contextual understanding via three dedicated tasks: reconstructing masked road networks to learn spatial correlations, agent trajectories to model social interactions, and navigation routes to capture destination intents. To further align vehicle dynamics and safety constraints, we incorporate a local sub-planning task predicting the ego-vehicle's near-term trajectory segment conditioned on earlier segment. This pretrained model is subsequently fine-tuned on downstream tasks to jointly generate the prediction and planning trajectories. Experiments on large-scale datasets demonstrate that Plan-MAE outperforms current methods on the planning metrics by a large margin and can serve as an important pre-training step for learning-based motion planner.

cs.RO↗

arXiv2025

Causal-Entity Reflected Egocentric Traffic Accident Video Synthesis

Egocentricly comprehending the causes and effects of car accidents is crucial for the safety of self-driving cars, and synthesizing causal-entity reflected accident videos can facilitate the capability test to respond to unaffordable accidents in reality. However, incorporating causal relations as seen in real-world videos into synthetic videos remains challenging. This work argues that precisely identifying the accident participants and capturing their related behaviors are of critical importance. In this regard, we propose a novel diffusion model, Causal-VidSyn, for synthesizing egocentric traffic accident videos. To enable causal entity grounding in video diffusion, Causal-VidSyn leverages the cause descriptions and driver fixations to identify the accident participants and behaviors, facilitated by accident reason answering and gaze-conditioned selection modules. To support Causal-VidSyn, we further construct Drive-Gaze, the largest driver gaze dataset (with 1.54M frames of fixations) in driving accident scenarios. Extensive experiments show that Causal-VidSyn surpasses state-of-the-art video diffusion models in terms of frame quality and causal sensitivity in various tasks, including accident video editing, normal-to-accident video diffusion, and text-to-video generation.

cs.CV↗

arXiv2025

C2TE: Coordinated Constrained Task Execution Design for Ordering-Flexible Multi-Vehicle Platoon Merging

In this paper, we propose a distributed coordinated constrained task execution (C2TE) algorithm that enables a team of vehicles from different lanes to cooperatively merge into an {\it ordering-flexible platoon} maneuvering on the desired lane. Therein, the platoon is flexible in the sense that no specific spatial ordering sequences of vehicles are predetermined. To attain such a flexible platoon, we first separate the multi-vehicle platoon (MVP) merging mission into two stages, namely, pre-merging regulation and {\it ordering-flexible platoon} merging, and then formulate them into distributed constraint-based optimization problems. Particularly, by encoding longitudinal-distance regulation and same-lane collision avoidance subtasks into the corresponding control barrier function (CBF) constraints, the proposed algorithm in Stage 1 can safely enlarge sufficient longitudinal distances among adjacent vehicles. Then, by encoding lateral convergence, longitudinal-target attraction, and neighboring collision avoidance subtasks into CBF constraints, the proposed algorithm in Stage~2 can efficiently achieve the {\it ordering-flexible platoon}. Note that the {\it ordering-flexible platoon} is realized through the interaction of the longitudinal-target attraction and time-varying neighboring collision avoidance constraints simultaneously. Feasibility guarantee and rigorous convergence analysis are both provided under strong nonlinear couplings induced by flexible orderings. Finally, experiments using three autonomous mobile vehicles (AMVs) are conducted to verify the effectiveness and flexibility of the proposed algorithm, and extensive simulations are performed to demonstrate its robustness, adaptability, and scalability when tackling vehicles' sudden breakdown, new appearing, different number of lanes, mixed autonomy, and large-scale scenarios, respectively.

cs.RO↗

arXiv2025

Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving

End-to-end autonomous driving has emerged as a promising paradigm for directly mapping sensor inputs to planning maneuvers using learning-based modular integrations. However, existing imitation learning (IL)-based models suffer from generalization to hard cases, and a lack of corrective feedback loop under post-deployment. While reinforcement learning (RL) offers a potential solution to tackle hard cases with optimality, it is often hindered by overfitting to specific driving cases, resulting in catastrophic forgetting of generalizable knowledge and sample inefficiency. To overcome these challenges, we propose Reinforced Refinement with Self-aware Expansion (R2SE), a novel learning pipeline that constantly refines hard domain while keeping generalizable driving policy for model-agnostic end-to-end driving systems. Through reinforcement fine-tuning and policy expansion that facilitates continuous improvement, R2SE features three key components: 1) Generalist Pretraining with hard-case allocation trains a generalist imitation learning (IL) driving system while dynamically identifying failure-prone cases for targeted refinement; 2) Residual Reinforced Specialist Fine-tuning optimizes residual corrections using reinforcement learning (RL) to improve performance in hard case domain while preserving global driving knowledge; 3) Self-aware Adapter Expansion dynamically integrates specialist policies back into the generalist model, enhancing continuous performance improvement. Experimental results in closed-loop simulation and real-world datasets demonstrate improvements in generalization, safety, and long-horizon policy robustness over state-of-the-art E2E systems, highlighting the effectiveness of reinforce refinement for scalable autonomous driving.

cs.RO↗

arXiv2025

Directly Forecasting Belief for Reinforcement Learning with Delays

Reinforcement learning (RL) with delays is challenging as sensory perceptions lag behind the actual events: the RL agent needs to estimate the real state of its environment based on past observations. State-of-the-art (SOTA) methods typically employ recursive, step-by-step forecasting of states. This can cause the accumulation of compounding errors. To tackle this problem, our novel belief estimation method, named Directly Forecasting Belief Transformer (DFBT), directly forecasts states from observations without incrementally estimating intermediate states step-by-step. We theoretically demonstrate that DFBT greatly reduces compounding errors of existing recursively forecasting methods, yielding stronger performance guarantees. In experiments with D4RL offline datasets, DFBT reduces compounding errors with remarkable prediction accuracy. DFBT's capability to forecast state sequences also facilitates multi-step bootstrapping, thus greatly improving learning efficiency. On the MuJoCo benchmark, our DFBT-based method substantially outperforms SOTA baselines. Code is available at https://github.com/QingyuanWuNothing/DFBT.

cs.LG↗

arXiv2025

iPad: Iterative Proposal-centric End-to-End Autonomous Driving

End-to-end (E2E) autonomous driving systems offer a promising alternative to traditional modular pipelines by reducing information loss and error accumulation, with significant potential to enhance both mobility and safety. However, most existing E2E approaches directly generate plans based on dense bird's-eye view (BEV) grid features, leading to inefficiency and limited planning awareness. To address these limitations, we propose iterative Proposal-centric autonomous driving (iPad), a novel framework that places proposals - a set of candidate future plans - at the center of feature extraction and auxiliary tasks. Central to iPad is ProFormer, a BEV encoder that iteratively refines proposals and their associated features through proposal-anchored attention, effectively fusing multi-view image data. Additionally, we introduce two lightweight, proposal-centric auxiliary tasks - mapping and prediction - that improve planning quality with minimal computational overhead. Extensive experiments on the NAVSIM and CARLA Bench2Drive benchmarks demonstrate that iPad achieves state-of-the-art performance while being significantly more efficient than prior leading methods.

cs.CV↗

arXiv2025

Crafting Physical Adversarial Examples by Combining Differentiable and Physically Based Renders

Recently we have witnessed progress in hiding road vehicles against object detectors through adversarial camouflage in the digital world. The extension of this technique to the physical world is crucial for testing the robustness of autonomous driving systems. However, existing methods do not show good performances when applied to the physical world. This is partly due to insufficient photorealism in training examples, and lack of proper physical realization methods for camouflage. To generate a robust adversarial camouflage suitable for real vehicles, we propose a novel method called PAV-Camou. We propose to adjust the mapping from the coordinates in the 2D map to those of corresponding 3D model. This process is critical for mitigating texture distortion and ensuring the camouflage's effectiveness when applied in the real world. Then we combine two renderers with different characteristics to obtain adversarial examples that are photorealistic that closely mimic real-world lighting and texture properties. The method ensures that the generated textures remain effective under diverse environmental conditions. Our adversarial camouflage can be optimized and printed in the form of 2D patterns, allowing for direct application on real vehicles. Extensive experiments demonstrated that our proposed method achieved good performance in both the digital world and the physical world.

cs.GR↗

arXiv2025

Planning for quasi-static manipulation tasks via an intrinsic haptic metric: a book insertion case study

Contact-rich manipulation often requires strategic interactions with objects, such as pushing to accomplish specific tasks. We propose a novel scenario where a robot inserts a book into a crowded shelf by pushing aside neighboring books to create space before slotting the new book into place. Classical planning algorithms fail in this context due to limited space and their tendency to avoid contact. Additionally, they do not handle indirectly manipulable objects or consider force interactions. Our key contributions are: i) reframing quasi-static manipulation as a planning problem on an implicit manifold derived from equilibrium conditions; ii) utilizing an intrinsic haptic metric instead of ad-hoc cost functions; and iii) proposing an adaptive algorithm that simultaneously updates robot states, object positions, contact points, and haptic distances. We evaluate our method on a crowded bookshelf insertion task, and it can be generally applied to rigid body manipulation tasks. We propose proxies to capture contact points and forces, with superellipses to represent objects. This simplified model guarantees differentiability. Our framework autonomously discovers strategic wedging-in policies while our simplified contact model achieves behavior similar to real world scenarios. We also vary the stiffness and initial positions to analyze our framework comprehensively. The video can be found at https://youtu.be/eab8umZ3AQ0.

cs.RO↗

arXiv2025

CL-CoTNav: Closed-Loop Hierarchical Chain-of-Thought for Zero-Shot Object-Goal Navigation with Vision-Language Models

Visual Object Goal Navigation (ObjectNav) requires a robot to locate a target object in an unseen environment using egocentric observations. However, decision-making policies often struggle to transfer to unseen environments and novel target objects, which is the core generalization problem. Traditional end-to-end learning methods exacerbate this issue, as they rely on memorizing spatial patterns rather than employing structured reasoning, limiting their ability to generalize effectively. In this letter, we introduce Closed-Loop Hierarchical Chain-of-Thought Navigation (CL-CoTNav), a vision-language model (VLM)-driven ObjectNav framework that integrates structured reasoning and closed-loop feedback into navigation decision-making. To enhance generalization, we fine-tune a VLM using multi-turn question-answering (QA) data derived from human demonstration trajectories. This structured dataset enables hierarchical Chain-of-Thought (H-CoT) prompting, systematically extracting compositional knowledge to refine perception and decision-making, inspired by the human cognitive process of locating a target object through iterative reasoning steps. Additionally, we propose a Closed-Loop H-CoT mechanism that incorporates detection and reasoning confidence scores into training. This adaptive weighting strategy guides the model to prioritize high-confidence data pairs, mitigating the impact of noisy inputs and enhancing robustness against hallucinated or incorrect reasoning. Extensive experiments in the AI Habitat environment demonstrate CL-CoTNav's superior generalization to unseen scenes and novel object categories. Our method consistently outperforms state-of-the-art approaches in navigation success rate (SR) and success weighted by path length (SPL) by 22.4\%. We release our datasets, models, and supplementary videos on our project page.

cs.RO↗

arXiv2025

A Planning Framework for Stable Robust Multi-Contact Manipulation

While modeling multi-contact manipulation as a quasi-static mechanical process transitioning between different contact equilibria, we propose formulating it as a planning and optimization problem, explicitly evaluating (i) contact stability and (ii) robustness to sensor noise. Specifically, we conduct a comprehensive study on multi-manipulator control strategies, focusing on dual-arm execution in a planar peg-in-hole task and extending it to the Multi-Manipulator Multiple Peg-in-Hole (MMPiH) problem to explore increased task complexity. Our framework employs Dynamic Movement Primitives (DMPs) to parameterize desired trajectories and Black-Box Optimization (BBO) with a comprehensive cost function incorporating friction cone constraints, squeeze forces, and stability considerations. By integrating parallel scenario training, we enhance the robustness of the learned policies. To evaluate the friction cone cost in experiments, we test the optimal trajectories computed for various contact surfaces, i.e., with different coefficients of friction. The stability cost is analytical explained and tested its necessity in simulation. The robustness performance is quantified through variations of hole pose and chamfer size in simulation and experiment. Results demonstrate that our approach achieves consistently high success rates in both the single peg-in-hole and multiple peg-in-hole tasks, confirming its effectiveness and generalizability. The video can be found at https://youtu.be/IU0pdnSd4tE.

cs.RO↗

arXiv2025

Path Planning in Complex Environments with Superquadrics and Voronoi-Based Orientation

Path planning in narrow passages is a challenging problem in various applications. Traditional planning algorithms often face challenges in complex environments like mazes and traps, where narrow entrances require special orientation control for successful navigation. In this work, we present a novel approach that combines superquadrics (SQ) representation and Voronoi diagrams to solve the narrow passage problem in both 2D and 3D environment. Our method utilizes the SQ formulation to expand obstacles, eliminating impassable passages, while Voronoi hyperplane ensures maximum clearance path. Additionally, the hyperplane provides a natural reference for robot orientation, aligning its long axis with the passage direction. We validate our framework through a 2D object retrieval task and 3D drone simulation, demonstrating that our approach outperforms classical planners and a cutting-edge drone planner by ensuring passable trajectories with maximum clearance.

cs.RO↗

arXiv2025

Interact, Instruct to Improve: A LLM-Driven Parallel Actor-Reasoner Framework for Enhancing Autonomous Vehicle Interactions

Autonomous Vehicles (AVs) have entered the commercialization stage, but their limited ability to interact and express intentions still poses challenges in interactions with Human-driven Vehicles (HVs). Recent advances in large language models (LLMs) enable bidirectional human-machine communication, but the conflict between slow inference speed and the need for real-time decision-making challenges practical deployment. To address these issues, this paper introduces a parallel Actor-Reasoner framework designed to enable explicit bidirectional AV-HV interactions across multiple scenarios. First, by facilitating interactions between the LLM-driven Reasoner and heterogeneous simulated HVs during training, an interaction memory database, referred to as the Actor, is established. Then, by introducing the memory partition module and the two-layer memory retrieval module, the Actor's ability to handle heterogeneous HVs is significantly enhanced. Ablation studies and comparisons with other decision-making methods demonstrate that the proposed Actor-Reasoner framework significantly improves safety and efficiency. Finally, with the combination of the external Human-Machine Interface (eHMI) information derived from Reasoner's reasoning and the feasible action solutions retrieved from the Actor, the effectiveness of the proposed Actor-Reasoner is confirmed in multi-scenario field interactions. Our code is available at https://github.com/FanGShiYuu/Actor-Reasoner.

cs.RO↗

arXiv2024

WiseAD: Knowledge Augmented End-to-End Autonomous Driving with Vision-Language Model

The emergence of general human knowledge and impressive logical reasoning capacity in rapidly progressed vision-language models (VLMs) have driven increasing interest in applying VLMs to high-level autonomous driving tasks, such as scene understanding and decision-making. However, an in-depth study on the relationship between knowledge proficiency, especially essential driving expertise, and closed-loop autonomous driving performance requires further exploration. In this paper, we investigate the effects of the depth and breadth of fundamental driving knowledge on closed-loop trajectory planning and introduce WiseAD, a specialized VLM tailored for end-to-end autonomous driving capable of driving reasoning, action justification, object recognition, risk analysis, driving suggestions, and trajectory planning across diverse scenarios. We employ joint training on driving knowledge and planning datasets, enabling the model to perform knowledge-aligned trajectory planning accordingly. Extensive experiments indicate that as the diversity of driving knowledge extends, critical accidents are notably reduced, contributing 11.9% and 12.4% improvements in the driving score and route completion on the Carla closed-loop evaluations, achieving state-of-the-art performance. Moreover, WiseAD also demonstrates remarkable performance in knowledge evaluations on both in-domain and out-of-domain datasets.

cs.CV↗

arXiv2024

Integrating Decision-Making Into Differentiable Optimization Guided Learning for End-to-End Planning of Autonomous Vehicles

We address the decision-making capability within an end-to-end planning framework that focuses on motion prediction, decision-making, and trajectory planning. Specifically, we formulate decision-making and trajectory planning as a differentiable nonlinear optimization problem, which ensures compatibility with learning-based modules to establish an end-to-end trainable architecture. This optimization introduces explicit objectives related to safety, traveling efficiency, and riding comfort, guiding the learning process in our proposed pipeline. Intrinsic constraints resulting from the decision-making task are integrated into the optimization formulation and preserved throughout the learning process. By integrating the differentiable optimizer with a neural network predictor, the proposed framework is end-to-end trainable, aligning various driving tasks with ultimate performance goals defined by the optimization objectives. The proposed framework is trained and validated using the Waymo Open Motion dataset. The open-loop testing reveals that while the planning outcomes using our method do not always resemble the expert trajectory, they consistently outperform baseline approaches with improved safety, traveling efficiency, and riding comfort. The closed-loop testing further demonstrates the effectiveness of optimizing decisions and improving driving performance. Ablation studies demonstrate that the initialization provided by the learning-based prediction module is essential for the convergence of the optimizer as well as the overall driving performance.

cs.RO↗

arXiv2024

Variational Delayed Policy Optimization

In environments with delayed observation, state augmentation by including actions within the delay window is adopted to retrieve Markovian property to enable reinforcement learning (RL). However, state-of-the-art (SOTA) RL techniques with Temporal-Difference (TD) learning frameworks often suffer from learning inefficiency, due to the significant expansion of the augmented state space with the delay. To improve learning efficiency without sacrificing performance, this work introduces a novel framework called Variational Delayed Policy Optimization (VDPO), which reformulates delayed RL as a variational inference problem. This problem is further modelled as a two-step iterative optimization problem, where the first step is TD learning in the delay-free environment with a small state space, and the second step is behaviour cloning which can be addressed much more efficiently than TD learning. We not only provide a theoretical analysis of VDPO in terms of sample complexity and performance, but also empirically demonstrate that VDPO can achieve consistent performance with SOTA methods, with a significant enhancement of sample efficiency (approximately 50\% less amount of samples) in the MuJoCo benchmark.

cs.LG↗