arXiv subjects

Jicong Ao

Publications and source records attributed to Jicong Ao.

5 recordsLinked to original sources

arXiv2026

AssemLM: A Spatial Reasoning Multimodal Large Language Model for Robotic Assembly

Spatial reasoning is a fundamental capability for embodied intelligence, especially for fine-grained manipulation tasks such as robotic assembly. Recent methods based on vision-language models (VLMs) largely rely on coarse 2D perception and struggle to perform accurate reasoning over complex 3D geometry. To address this limitation, we propose AssemLM, a spatial multimodal large language model for robotic assembly that integrates assembly manuals, point clouds, and textual instructions to predict task-critical 6D assembly poses with explicit geometric understanding. To bridge raw 3D perception and high-level linguistic reasoning, AssemLM employs a specialized point cloud encoder to extract fine-grained geometric and rotational features for accurate 3D spatial reasoning in assembly tasks. In addition, we introduce AssemBench, a large-scale benchmark for assembly-oriented spatial reasoning with over 900K multimodal samples and precise 6D pose annotations, extending evaluation from 2D grounding to full 3D geometric inference. Extensive experiments and real-robot evaluations demonstrate that AssemLM achieves state-of-the-art 6D pose reasoning performance and effectively supports fine-grained, multi-step assembly tasks in real-world settings. Code, models, and the AssemBench dataset will be made publicly available.

cs.RO↗

arXiv2026

Beyond Short-Horizon: VQ-Memory for Robust Long-Horizon Manipulation in Non-Markovian Simulation Benchmarks

The high cost of collecting real-robot data has made robotic simulation a scalable platform for both evaluation and data generation. Yet most existing benchmarks concentrate on simple manipulation tasks such as pick-and-place, failing to capture the non-Markovian characteristics of real-world tasks and the complexity of articulated object interactions. To address this limitation, we present RuleSafe, a new articulated manipulation benchmark built upon a scalable LLM-aided simulation framework. RuleSafe features safes with diverse unlocking mechanisms, such as key locks, password locks, and logic locks, which require different multi-stage reasoning and manipulation strategies. These LLM-generated rules produce non-Markovian and long-horizon tasks that require temporal modeling and memory-based reasoning. We further propose VQ-Memory, a compact and structured temporal representation that uses vector-quantized variational autoencoders (VQ-VAEs) to encode past proprioceptive states into discrete latent tokens. This representation filters low-level noise while preserving high-level task-phase context, providing lightweight yet robust temporal cues that are compatible with existing Vision-Language-Action models (VLA). Extensive experiments on state-of-the-art VLA models and diffusion policies show that VQ-Memory consistently improves long-horizon planning, enhances generalization to unseen configurations, and enables more efficient manipulation with reduced computational cost. Project page: vqmemory.github.io

cs.RO↗

arXiv2025

HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning

For robotic manipulation, existing robotics datasets and simulation benchmarks predominantly cater to robot-arm platforms. However, for humanoid robots equipped with dual arms and dexterous hands, simulation tasks and high-quality demonstrations are notably lacking. Bimanual dexterous manipulation is inherently more complex, as it requires coordinated arm movements and hand operations, making autonomous data collection challenging. This paper presents HumanoidGen, an automated task creation and demonstration collection framework that leverages atomic dexterous operations and LLM reasoning to generate relational constraints. Specifically, we provide spatial annotations for both assets and dexterous hands based on the atomic operations, and perform an LLM planner to generate a chain of actionable spatial constraints for arm movements based on object affordances and scenes. To further improve planning ability, we employ a variant of Monte Carlo tree search to enhance LLM reasoning for long-horizon tasks and insufficient annotation. In experiments, we create a novel benchmark with augmented scenarios to evaluate the quality of the collected data. The results show that the performance of the 2D and 3D diffusion policies can scale with the generated dataset. Project page is https://openhumanoidgen.github.io.

cs.RO↗

arXiv2025

LLM-as-BT-Planner: Leveraging LLMs for Behavior Tree Generation in Robot Task Planning

Robotic assembly tasks remain an open challenge due to their long horizon nature and complex part relations. Behavior trees (BTs) are increasingly used in robot task planning for their modularity and flexibility, but creating them manually can be effort-intensive. Large language models (LLMs) have recently been applied to robotic task planning for generating action sequences, yet their ability to generate BTs has not been fully investigated. To this end, we propose LLM-as-BT-Planner, a novel framework that leverages LLMs for BT generation in robotic assembly task planning. Four in-context learning methods are introduced to utilize the natural language processing and inference capabilities of LLMs for producing task plans in BT format, reducing manual effort while ensuring robustness and comprehensibility. Additionally, we evaluate the performance of fine-tuned smaller LLMs on the same tasks. Experiments in both simulated and real-world settings demonstrate that our framework enhances LLMs' ability to generate BTs, improving success rate through in-context learning and supervised fine-tuning.

cs.RO↗

arXiv2024

Behavior Tree Generation using Large Language Models for Sequential Manipulation Planning with Human Instructions and Feedback

In this work, we propose an LLM-based BT generation framework to leverage the strengths of both for sequential manipulation planning. To enable human-robot collaborative task planning and enhance intuitive robot programming by nonexperts, the framework takes human instructions to initiate the generation of action sequences and human feedback to refine BT generation in runtime. All presented methods within the framework are tested on a real robotic assembly example, which uses a gear set model from the Siemens Robot Assembly Challenge. We use a single manipulator with a tool-changing mechanism, a common practice in flexible manufacturing, to facilitate robust grasping of a large variety of objects. Experimental results are evaluated regarding success rate, logical coherence, executability, time consumption, and token consumption. To our knowledge, this is the first human-guided LLM-based BT generation framework that unifies various plausible ways of using LLMs to fully generate BTs that are executable on the real testbed and take into account granular knowledge of tool use.

cs.RO↗