Model-based reinforcement learning (MBRL) has shown significant potential in robotics due to its high sample efficiency and planning capability. However, extending MBRL to multi-robot cooperation remains challenging due to the complexity of joint dynamics and the reliance on synchronous communication. SeqWM employs independent, autoregressive agent-wise world models to represent joint dynamics, where each agent generates its future trajectory and plans its actions based on the predictions of its predecessors. This design lowers modeling complexity, alleviates the reliance on communication synchronization, and enables the emergence of advanced cooperative behaviors through explicit intention sharing. Experiments in challenging simulated environments (Bi-DexHands and Multi-Quad) demonstrate that SeqWM outperforms existing state-of-the-art model-based and model-free baselines in both overall performance and sample efficiency, while exhibiting advanced cooperative behaviors such as predictive adaptation, temporal alignment, and role division. Furthermore, SeqWM has been success fully deployed on physical quadruped robots, demonstrating its effectiveness in real-world multi-robot systems. Demos and code are available at: https://sites.google.com/view/seqwm-marl

Generating high-quality motion plans for multiple robot arms is challenging due to the high dimensionality of the system and the potential for inter-arm collisions. Traditional motion planning methods often produce motions that are suboptimal in terms of smoothness and execution time for multi-arm systems. Post-processing via shortcutting is a common approach to improve motion quality for efficient and smooth execution. However, in multi-arm scenarios, optimizing one arm's motion must not introduce collisions with other arms. Although existing multi-arm planning works often use some form of shortcutting techniques, their exact methodology and impact on performance are often vaguely described. In this work, we present a comprehensive study quantitatively comparing existing shortcutting methods for multi-arm trajectories across diverse simulated scenarios. We carefully analyze the pros and cons of each shortcutting method and propose two simple strategies for combining these methods to achieve the best performance-runtime tradeoff. Video, code, and dataset are available at https://philip-huang.github.io/mr-shortcut/.

Large language models (LLMs) have demonstrated strong performance in various robot control tasks. However, their deployment in real-world applications remains constrained. Even state-ofthe-art LLMs, such as GPT-o4mini, frequently produce invalid action plans that violate physical constraints, such as directing a robot to an unreachable location or causing collisions between robots. This issue primarily arises from a lack of awareness of these physical constraints during the reasoning process. To address this issue, we propose a novel framework that integrates reinforcement learning with verifiable rewards (RLVR) to incentivize knowledge of physical constraints into LLMs to induce constraints-aware reasoning during plan generation. In this approach, only valid action plans that successfully complete a control task receive positive rewards. We applied our method to two small-scale LLMs: a non-reasoning Qwen2.5-3B-Instruct and a reasoning Qwen3-4B. The experiment results demonstrate that constraint-aware small LLMs largely outperform large-scale models without constraints, grounded on both the BoxNet task and a newly developed BoxNet3D environment built using MuJoCo. This work highlights the effectiveness of grounding even small LLMs with physical constraints to enable scalable and efficient multi-robot control in complex, physically constrained environments.

-- Mobile robots increasingly operate alongside humans but are often out of sight, so that humans need to rely on the sounds of the robots to recognize their presence. For successful human-robot interaction (HRI), it is therefore crucial to understand how humans perceive robots by their consequential sounds, i.e., operating noise. Prior research suggests that the sound of a quadruped Go1 is more detectable than that of a wheeled T urtlebot. This study builds on this and examines the human ability to localize consequential sounds of three robots (quadruped Go1, wheeled T urtlebot 2i, wheeled HSR) in Virtual Reality. In a within-subjects design, we assessed participants' localization performance for the robots with and without an acoustic vehicle alerting system (A V AS) for two velocities (0.3, 0.8 m/s) and two trajectories (head-on, radial). In each trial, participants were presented with the sound of a moving robot for 3 s and were tasked to point at its final position (localization task). Localization errors were measured as the absolute angular difference between the participants' estimated and the actual robot position. Results showed that the robot type significantly influenced the localization accuracy and precision, with the sound of the wheeled HSR (especially without A V AS) performing worst under all experimental conditions. Surprisingly, participants rated the HSR sound as more positive, less annoying, and more trustworthy than the T urtlebot and Go1 sound. This reveals a tension between subjective evaluation and objective auditory localization performance. Our findings highlight consequential robot sounds as a critical factor for designing intuitive and effective HRI, with implications for human-centered robot design and social navigation.

This paper presents two industry-grade datasets captured during an 8-hour continuous operation of the manufacturing assembly line at the Future Factories Lab, University of South Carolina, on 08/13/2024. The datasets adhere to industry standards, covering communication protocols, actuators, control mechanisms, transducers, sensors, and cameras. Data collection utilized both integrated and external sensors throughout the laboratory, including sensors embedded within the actuators and externally installed devices. Additionally, high-performance cameras captured key aspects of the operation. In a prior experiment [1], a 30-hour continuous run was conducted, during which all anomalies were documented. Maintenance procedures were subsequently implemented to reduce potential errors and operational disruptions. The two datasets include: (1) a time-series analog dataset, and (2) a multi-modal time-series dataset containing synchronized system data and images. These datasets aim to support future research in advancing manufacturing processes by providing a platform for testing novel algorithms without the need to recreate physical manufacturing environments. Moreover, the datasets are open-source and designed to facilitate the training of artificial intelligence models, streamlining research by offering comprehensive, ready-to-use resources for various applications and projects.

Industrial robotic applications such as spraying, welding, and additive manufacturing frequently require fast, accurate, and uniform motion along a 3D spatial curve. To increase process throughput, some manufacturers propose a dual-robot setup to overcome the speed limitation of a single robot. Industrial robot motion is programmed through waypoints connected by motion primitives (Cartesian linear and circular paths and linear joint paths at constant Cartesian speed). The actual robot motion is affected by the blending between these motion primitives and the pose of the robot (an outstretched/close to singularity pose tends to have larger path-tracking errors). Choosing the waypoints and the speed along each motion segment to achieve the performance requirement is challenging. At present, there is no automated solution, and laborious manual tuning by robot experts is needed to approach the desired performance. In this paper, we present a systematic three-step approach to designing and programming a dual-robot system to optimize system performance. The first step is to select the relative placement between the two robots based on the specified relative motion path. The second step is to select the relative waypoints and the motion primitives. The final step is to update the waypoints iteratively based on the actual relative motion. Waypoint iteration is first executed in simulation and then completed using the actual robots. For performance measures, we use the mean path speed subject to the relative position and orientation constraints and the path speed uniformity constraint. We have demonstrated the effectiveness of this method with ABB and FANUC robots on two challenging test curves. The performance improvement over the current industrial practice baseline is over 300%. Compared to the optimized single-arm case that we have previously reported, the improvement is over 14%.

Two industry-grade datasets are presented in this paper that were collected at the Future Factories Lab at the University of South Carolina on December 11th and 12th of 2023. These datasets are generated by a manufacturing assembly line that utilizes industrial standards with respect to actuators, control mechanisms, and transducers. The two datasets were both generated simultaneously by operating the assembly line for 30 consecutive hours (with minor filtering) and collecting data from sensors equipped throughout the system. During operation, defects were also introduced into the assembly operation by manually removing parts needed for the final assembly. The datasets generated include a time series analog dataset and the other is a time series multi-modal dataset which includes images of the system alongside the analog data. These datasets were generated with the objective of providing tools to further the research towards enhancing intelligence in manufacturing. Real manufacturing datasets can be scarce let alone datasets with anomalies or defects. As such these datasets hope to address this gap and provide researchers with a foundation to build and train Artificial Intelligence models applicable for the manufacturing industry. Finally, these datasets are the first iteration of published data from the future Factories lab and can be further adjusted to fit more researchers needs moving forward.

Several task and motion planning algorithms have been proposed recently to design paths for mobile robot teams with collaborative high-level missions specified using formal languages, such as Linear Temporal Logic (LTL). However, the designed paths often lack reactivity to failures of robot capabilities (e.g., sensing, mobility, or manipulation) that can occur due to unanticipated events (e.g., human intervention or system malfunctioning) which in turn may compromise mission performance. To address this novel challenge, in this paper, we propose a new resilient mission planning algorithm for teams of heterogeneous robots with collaborative LTL missions. The robots are heterogeneous with respect to their capabilities while the mission requires applications of these skills at certain areas in the environment in a temporal/logical order. The proposed method designs paths that can adapt to unexpected failures of robot capabilities. This is accomplished by re-allocating sub-tasks to the robots based on their currently functioning skills while minimally disrupting the existing team motion plans. We provide experiments and theoretical guarantees demonstrating the efficiency and resiliency of the proposed algorithm.

This paper proposes the cooperative use of zero velocity update (ZU) in a decentralized extended Kalman filter (DEKF) based localization algorithm for multi-robot systems. The filter utilizes inertial measurement unit (IMU), ultra-wideband (UWB), and odometry velocity measurements to improve the localization performance of the system in the presence of a GNSS-denied environment. The contribution of this work is to evaluate the benefits of using ZU in a DEKF-based localization algorithm. The algorithm is tested with real hardware in a video motion capture facility and a Robot Operating System (ROS) based simulation environment for unmanned ground vehicles (UGV). Both simulation and real-world experiments are performed to show the effectiveness of using ZU in one robot to reinstate the localization of other robots in a multi-robot system. Experimental results from GNSS-denied simulation and real-world environments show that using ZU with simple heuristics in the DEKF significantly improves the 3D localization accuracy.

With the increasing need for multi-robot for exploring the unknown region in a challenging environment, efficient collaborative exploration strategies are needed for achieving such feat. A frontier-based Rapidly-Exploring Random Tree (RRT) exploration can be deployed to explore an unknown environment. However, its' greedy behavior causes multiple robots to explore the region with the highest revenue, which leads to massive overlapping in exploration process. To address this issue, we present a temporal memory-based RRT (TM-RRT) exploration strategy for multi-robot to perform robust exploration in an unknown environment. It computes adaptive duration for each frontier assigned and calculates the frontier's revenue based on the relative position of each robot. In addition, each robot is equipped with a memory consisting of frontier assigned and share among fleets to prevent repeating assignment of same frontier. Through both simulation and actual deployment, we have shown the robustness of TM-RRT exploration strategy by completing the exploration in a 25.0m x 54.0m (1350.0m2) area, while the conventional RRT exploration strategy falls short.