Searcharxiv⌕ Search

arXiv subjects

Yimin Tang

Publications and source records attributed to Yimin Tang.

12 recordsLinked to original sources
arXiv2026

Search-Aided Joint Agent-Environment Reinforcement Learning for Robust Lifelong Multi-Agent Path Finding with Rotations

Lifelong Multi-Agent Path Finding (LMAPF) requires repeatedly planning collision-free paths for agents that continuously receive new goals upon reaching their current ones. While many learning-based planners have been proposed for LMAPF, most rely on oversimplified kinematic assumptions that may overlook motion constraints critical to real-world performance. In this work, we study a more realistic LMAPF model derived from many real-world automated warehouse systems, termed LMAPF-R2, which incorporates robust safety constraints and in-place rotation constraints. These constraints substantially increase coordination difficulty, particularly in highly constrained spaces. To address these challenges, we propose Search-Aided Joint Reinforcement Learning (SJRL). We first augment neural policies with Causal PIBT, a single-step search-based planner that resolves agents' collisions and propagates their intentions. We then introduce a unified RL formulation that jointly optimizes agent and environment policies, where the environment policy learns graph edge costs to provide global movement guidance via backward Dijkstra search. Experiments demonstrate that SJRL achieves significant improvements over the strong search-based planner, Causal-PIBT, across multiple high-density maps. We further validate SJRL in a challenging mixed-reality warehouse environment with 8 physical robots and 248 virtual robots.

cs.RO↗
arXiv2026

Judgelight: Trajectory-Level Post-Optimization for Multi-Agent Path Finding via Closed-Subwalk Collapsing

Multi-Agent Path Finding (MAPF) is an NP-hard problem with applications in warehouse automation and multi-robot coordination. Learning-based MAPF solvers offer fast and scalable planning but often produce feasible trajectories that contain unnecessary or oscillatory movements. We propose Judgelight, a post-optimization layer that improves trajectory quality after a MAPF solver generates a feasible schedule. Judgelight collapses closed subwalks in agents' trajectories to remove redundant movements while preserving all feasibility constraints. We formalize this process as MAPF-Collapse, prove that it is NP-hard, and present an exact optimization approach by formulating it as integer linear programming (ILP) problem. Experimental results show Judgelight consistently reduces solution cost by around 20%, particularly for learning-based solvers, producing trajectories that are better suited for real-world deployment.

cs.RO↗
arXiv2025

Bias as a Virtue: Rethinking Generalization under Distribution Shifts

Machine learning models often degrade when deployed on data distributions different from their training data. Challenging conventional validation paradigms, we demonstrate that higher in-distribution (ID) bias can lead to better out-of-distribution (OOD) generalization. Our Adaptive Distribution Bridge (ADB) framework implements this insight by introducing controlled statistical diversity during training, enabling models to develop bias profiles that effectively generalize across distributions. Empirically, we observe a robust negative correlation where higher ID bias corresponds to lower OOD error--a finding that contradicts standard practices focused on minimizing validation error. Evaluation on multiple datasets shows our approach significantly improves OOD generalization. ADB achieves robust mean error reductions of up to 26.8% compared to traditional cross-validation, and consistently identifies high-performing training strategies, evidenced by percentile ranks often exceeding 74.4%. Our work provides both a practical method for improving generalization and a theoretical framework for reconsidering the role of bias in robust machine learning.

cs.LG↗
arXiv2025

RAILGUN: A Unified Convolutional Policy for Multi-Agent Path Finding Across Different Environments and Tasks

Multi-Agent Path Finding (MAPF), which focuses on finding collision-free paths for multiple robots, is crucial for applications ranging from aerial swarms to warehouse automation. Solving MAPF is NP-hard so learning-based approaches for MAPF have gained attention, particularly those leveraging deep neural networks. Nonetheless, despite the community's continued efforts, all learning-based MAPF planners still rely on decentralized planning due to variability in the number of agents and map sizes. We have developed the first centralized learning-based policy for MAPF problem called RAILGUN. RAILGUN is not an agent-based policy but a map-based policy. By leveraging a CNN-based architecture, RAILGUN can generalize across different maps and handle any number of agents. We collect trajectories from rule-based methods to train our model in a supervised way. In experiments, RAILGUN outperforms most baseline methods and demonstrates great zero-shot generalization capabilities on various tasks, maps and agent numbers that were not seen in the training dataset.

cs.RO↗
arXiv2025

Accelerating Focal Search in Multi-Agent Path Finding with Tighter Lower Bounds

Multi-Agent Path Finding (MAPF) involves finding collision-free paths for multiple agents while minimizing a cost function--an NP-hard problem. Bounded suboptimal methods like Enhanced Conflict-Based Search (ECBS) and Explicit Estimation CBS (EECBS) balance solution quality with computational efficiency using focal search mechanisms. While effective, traditional focal search faces a limitation: the lower bound (LB) value determining which nodes enter the FOCAL list often increases slowly in early search stages, resulting in a constrained search space that delays finding valid solutions. In this paper, we propose a novel bounded suboptimal algorithm, double-ECBS (DECBS), to address this issue by first determining the maximum LB value and then employing a best-first search guided by this LB to find a collision-free path. Experimental results demonstrate that DECBS outperforms ECBS in most test cases and is compatible with existing optimization techniques. DECBS can reduce nearly 30% high-level CT nodes and 50% low-level focal search nodes. When agent density is moderate to high, DECBS achieves a 23.5% average runtime improvement over ECBS with identical suboptimality bounds and optimizations.

cs.MA↗
arXiv2025

Enhancing Lifelong Multi-Agent Path Finding with Cache Mechanism

Multi-Agent Path Finding (MAPF), which focuses on finding collision-free paths for multiple robots, is crucial in autonomous warehouse operations. Lifelong MAPF (L-MAPF), where agents are continuously reassigned new targets upon completing their current tasks, offers a more realistic approximation of real-world warehouse scenarios. While cache storage systems can enhance efficiency and reduce operational costs, existing approaches primarily rely on expectations and mathematical models, often without adequately addressing the challenges of multi-robot planning and execution. In this paper, we introduce a novel mechanism called Lifelong MAPF with Cache Mechanism (L-MAPF-CM), which integrates high-level cache storage with low-level path planning. We have involved a new type of map grid called cache for temporary item storage. Additionally, we involved a task assigner (TA) with a locking mechanism to bridge the gap between the new cache grid and L-MAPF algorithm. The TA dynamically allocates target locations to agents based on their status in various scenarios. We evaluated L-MAPF-CM using different cache replacement policies and task distributions. L-MAPF-CM has demonstrated performance improvements particularly with high cache hit rates and smooth traffic conditions.

cs.RO↗
arXiv2024

Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism

Transformers have a quadratic scaling of computational complexity with input size, which limits the input context window size of large language models (LLMs) in both training and inference. Meanwhile, retrieval-augmented generation (RAG) besed models can better handle longer contexts by using a retrieval system to filter out unnecessary information. However, most RAG methods only perform retrieval based on the initial query, which may not work well with complex questions that require deeper reasoning. We introduce a novel approach, Inner Loop Memory Augmented Tree Retrieval (ILM-TR), involving inner-loop queries, based not only on the query question itself but also on intermediate findings. At inference time, our model retrieves information from the RAG system, integrating data from lengthy documents at various levels of abstraction. Based on the information retrieved, the LLM generates texts stored in an area named Short-Term Memory (STM) which is then used to formulate the next query. This retrieval process is repeated until the text in STM converged. Our experiments demonstrate that retrieval with STM offers improvements over traditional retrieval-augmented LLMs, particularly in long context tests such as Multi-Needle In A Haystack (M-NIAH) and BABILong.

cs.CL↗
arXiv2024

ITA-ECBS: A Bounded-Suboptimal Algorithm for the Combined Target-Assignment and Path-Finding Problem

Multi-Agent Path Finding (MAPF), i.e., finding collision-free paths for multiple robots, plays a critical role in many applications. Sometimes, assigning a target to each agent also presents a challenge. The Combined Target-Assignment and Path-Finding (TAPF) problem, a variant of MAPF, requires one to simultaneously assign targets to agents and plan collision-free paths for agents. Several algorithms, including CBM, CBS-TA, and ITA-CBS, optimally solve the TAPF problem, with ITA-CBS being the leading algorithm for minimizing flowtime. However, the only existing bounded-suboptimal algorithm ECBS-TA is derived from CBS-TA rather than ITA-CBS. So, it faces the same issues as CBS-TA, such as searching through multiple constraint trees and spending too much time on finding the next-best target assignment. We introduce ITA-ECBS, the first bounded-suboptimal variant of ITA-CBS. Transforming ITA-CBS to its bounded-suboptimal variant is challenging because different constraint tree nodes can have different assignments of targets to agents. ITA-ECBS uses focal search to achieve efficiency and determines target assignments based on a new lower bound matrix. We show that it runs faster than ECBS-TA in 87.42% of 54,033 test cases.

cs.AI↗
arXiv2024

Caching-Augmented Lifelong Multi-Agent Path Finding

Multi-Agent Path Finding (MAPF), which involves finding collision-free paths for multiple robots, is crucial in various applications. Lifelong MAPF, where targets are reassigned to agents as soon as they complete their initial targets, offers a more accurate approximation of real-world warehouse planning. In this paper, we present a novel mechanism named Caching-Augmented Lifelong MAPF (CAL-MAPF), designed to improve the performance of Lifelong MAPF. We have developed a new type of map grid called cache for temporary item storage and replacement, and created a locking mechanism to improve the planning solution's stability. A task assigner (TA) is designed for CAL-MAPF to allocate target locations to agents and control agent status in different situations. CAL-MAPF has been evaluated using various cache replacement policies and input task distributions. We have identified three main factors significantly impacting CAL-MAPF performance through experimentation: suitable input task distribution, high cache hit rate, and smooth traffic. In general, CAL-MAPF has demonstrated potential for performance improvements in certain task distributions, map and agent configurations.

cs.RO↗
arXiv2023

Solving Multi-Agent Target Assignment and Path Finding with a Single Constraint Tree

Combined Target-Assignment and Path-Finding problem (TAPF) requires simultaneously assigning targets to agents and planning collision-free paths for agents from their start locations to their assigned targets. As a leading approach to address TAPF, Conflict-Based Search with Target Assignment (CBS-TA) leverages both K-best target assignments to create multiple search trees and Conflict-Based Search (CBS) to resolve collisions in each search tree. While being able to find an optimal solution, CBS-TA suffers from scalability due to the duplicated collision resolution in multiple trees and the expensive computation of K-best assignments. We therefore develop Incremental Target Assignment CBS (ITA-CBS) to bypass these two computational bottlenecks. ITA-CBS generates only a single search tree and avoids computing K-best assignments by incrementally computing new 1-best assignments during the search. We show that, in theory, ITA-CBS is guaranteed to find an optimal solution and, in practice, is computationally efficient.

cs.AI↗
arXiv2020

Multi-modal Transfer Learning for Grasping Transparent and Specular Objects

State-of-the-art object grasping methods rely on depth sensing to plan robust grasps, but commercially available depth sensors fail to detect transparent and specular objects. To improve grasping performance on such objects, we introduce a method for learning a multi-modal perception model by bootstrapping from an existing uni-modal model. This transfer learning approach requires only a pre-existing uni-modal grasping model and paired multi-modal image data for training, foregoing the need for ground-truth grasp success labels nor real grasp attempts. Our experiments demonstrate that our approach is able to reliably grasp transparent and reflective objects. Video and supplementary material are available at https://sites.google.com/view/transparent-specular-grasping.

cs.RO↗