asynchronous vision–arm scheduling

To address the lack of systematic response-time analysis and real-time scheduling guarantees in ROS 2’s multi-threaded executor, this paper introduces the first response-time analysis framework tailored to its kernel-level execution semantics. The framework supports modeling of arbitrary- and constrained-deadline task chains and precisely captures mutual exclusion among callback groups. We further propose a priority-driven scheduling enhancement mechanism that optimizes critical-path response times while preserving schedulability. Experimental evaluation on the Jetson AGX Xavier platform demonstrates that our framework yields tighter safe upper bounds on response time, reduces average response time of critical chains by a significant margin, and improves overall system schedulability by 23.6%.

ROS 2 lacks systematic support for real-time capabilities, hindering its applicability in high-determinism robotic systems. This work presents the first comprehensive taxonomy focused on real-time performance in ROS 2, integrating multidimensional research aspects including scheduling mechanisms, communication latency modeling based on DDS, multi-threaded executor design, hardware co-design (encompassing micro-ROS and GPU real-time management), and performance profiling tools. By establishing a unified evaluation framework grounded in key metrics such as response time and data timeliness, the study systematically reviews existing approaches, clarifies the trajectory of technical evolution, and offers developers a clear optimization roadmap. The proposed framework aims to advance the ROS community’s progress toward robust real-time robotic systems.

This work addresses the lack of cross-DAG priority-aware scheduling in ROS 2’s default executors, which leads to callback contention, priority inversion, and deadline instability—challenges that hinder the deployment of ROS 2 in safety-critical real-time systems. To overcome these limitations, we propose ReDAG-RT, a userspace global scheduling framework that, for the first time in ROS 2, enables deterministic execution with cross-DAG priority guarantees and concurrency control, without requiring modifications to the ROS 2 API or the underlying OS scheduler. ReDAG-RT integrates rate-monotonic theory through a rate-priority-driven global ready queue, per-DAG concurrency boundary enforcement, and recursive response-time analysis. Experimental results demonstrate that ReDAG-RT reduces deadline miss rates by 29.7% and 99th-percentile response times by 42.9% compared to native executors, while asymmetric concurrency boundaries further decrease interference by 40.8%.

This work addresses the challenge of serving policy inference for multiple heterogeneous robots from a remote GPU, where conventional batched scheduling fails to accommodate disparities in action chunk consumption rates, thereby limiting system throughput. The authors formulate this scenario as a scheduling problem and introduce Armory, a system featuring the first batched scheduling algorithm that explicitly accounts for heterogeneity in action chunk consumption—departing from traditional homogeneous assumptions to better align with the realities of robotic closed-loop control. Armory integrates remote GPU batched inference, deployment of Vision-Language-Action models, and coordination mechanisms for heterogeneous robots. Evaluations on both real-world and simulated robot clusters demonstrate its efficacy, achieving up to an 18% improvement in overall throughput compared to naive scheduling strategies.

Autonomous driving systems currently lack temporal analysis models and implementable software that jointly account for multi-rate asynchronous sensor streams and complex actuation chains, hindering guarantees of end-to-end timing correctness and functional safety. This work proposes, for the first time, a five-dimensional research gap framework—encompassing end-to-end latency, data freshness, temporal skew, probabilistic timing, and fail-safe mechanisms—from a co-design perspective of analytical models and system software. By integrating real-time scheduling theories (e.g., DAG-based and mixed-criticality systems), event- and time-triggered paradigms, ROS 2/Autoware architectures, communication optimizations, and runtime tracing techniques, the study systematically uncovers limitations in current approaches regarding constraint modeling, temporal metrics, resource abstraction, execution variability, and safety integration. The findings lay a theoretical and technical foundation for building a highly reliable temporal assurance framework for autonomous vehicles that is analyzable, observable, and deployable.

This work addresses the control performance limitations in tree-structured robotic systems caused by hierarchical data dependencies that introduce latency from perception to decision-making. To mitigate this, the authors propose FineMote, a novel framework that introduces, for the first time, a static scheduling mechanism tailored to tree-based robot models. FineMote objectifies heterogeneous low-level control logic and determines execution order statically at compile time based on the device tree, enabling low-overhead scheduling. The approach rigorously enforces deadline and priority constraints and derives a theoretical upper bound on intra-tree decision latency. Experimental evaluation on a physical robotic platform demonstrates substantial improvements in timing behavior and runtime responsiveness, confirming the framework’s effectiveness and practicality.

为解决GPU在VLA模型推理中利用率低的问题，提出KerColle框架，通过动态调度内核以提高执行效率。

This study addresses the challenges of real-time control and batched inference bottlenecks encountered when deploying Vision-Language-Action (VLA) models for embodied intelligence on edge devices. We systematically characterize the runtime behavior of four VLA models on edge GPUs and SoCs through single-inference profiling, closed-loop simulation, and hardware frequency scaling strategies. For the first time, this work reveals the transition mechanisms between memory and compute bottlenecks, demonstrating that no Pareto-optimal configuration exists, and proposes a theoretical framework for accuracy-speed-energy trade-offs. Furthermore, we quantify the trade-off effects of overlapping inference and execution. These findings provide critical guidance for the co-design of VLA model architectures, hardware selection, and runtime optimization strategies in resource-constrained edge environments.

This work addresses the discontinuity in visuomotor actions caused by misalignment between prediction and execution in asynchronous visual-language-action (VLA) policies. To resolve this, the authors propose FutureRTC, a framework that enables smooth, low-latency real-time control without modifying the original policy. FutureRTC predicts observations and states at the actual execution time through a state correction module, a motion-prior-guided visual representation prediction mechanism, and a policy consistency loss that aligns predicted context with actual inputs. Integrated with motion-aware feature propagation, forward state roll-out correction, and a plug-in compatible architecture, FutureRTC significantly improves task success rates in both simulation and real-world environments, yielding smoother trajectories, faster execution, and enhanced robustness to inference latency.

研究解决了事件相机在物体检测中因计算延迟导致的检测结果滞后问题，提出ChronoFuse方法预测未来状态以减少延迟影响。