More Like this

1. Robot-Assisted Pedestrian Regulation Based on Deep Reinforcement Learning

   https://doi.org/10.1109/TCYB.2018.2878977  

   Wan, Zhiqiang; Jiang, Chao; Fahad, Muhammad; Ni, Zhen; Guo, Yi; He, Haibo (January 2019, IEEE Transactions on Cybernetics)

   Pedestrian regulation can prevent crowd accidents and improve crowd safety in densely populated areas. Recent studies use mobile robots to regulate pedestrian flows for desired collective motion through the effect of passive human-robot interaction (HRI). This paper formulates a robot motion planning problem for the optimization of two merging pedestrian flows moving through a bottleneck exit. To address the challenge of feature representation of complex human motion dynamics under the effect of HRI, we propose using a deep neural network to model the mapping from the image input of pedestrian environments to the output of robot motion decisions. The robot motion planner is trained end-to-end using a deep reinforcement learning algorithm, which avoids hand-crafted feature detection and extraction, thus improving the learning capability for complex dynamic problems. Our proposed approach is validated in simulated experiments, and its performance is evaluated. The results demonstrate that the robot is able to find optimal motion decisions that maximize the pedestrian outflow in different flow conditions, and the pedestrian-accumulated outflow increases significantly compared to cases without robot regulation and with random robot motion. 

   more » « less
2. Online Dynamic Time Warping Algorithm for Human-Robot Imitation

   Taghavi, Nazita; Berdichevsky, Jacob; Balakrishnan, Namrata; Welch, Karla; Das, Sumit; Popa, Dan O. (June 2021, IEEE International Conference on Robotics and Automation)

   null (Ed.)

   In this paper, we propose a novel online algorithm for motion similarity measurements during human-robot interaction (HRI). Specifically, we formulate a Segment-based Online Dynamic Time Warping (SODTW) algorithm that can be used for understanding of repeated and cyclic human motions, in the context of rehabilitation or social interaction. The algorithm can estimate both the human-robot motion similarity and the time delay to initiate motion and combine these values as a metric to adaptively select appropriate robot imitation repertoires. We validated the algorithm offline by post-processing experimental data collected from a cohort of 55 subjects during imitation episodes with our social robot Zeno. Furthermore, we implemented the algorithm online on Zeno and collected further experimental results with 13 human subjects. These results show that the algorithm can reveal important features of human movement including the quality of motion and human reaction time to robot stimuli. Moreover, the robot can adapt to appropriate human motion speeds based on similarity measurements calculated using this algorithm, enabling future adaptive rehabilitation interventions for conditions such as Autism Spectrum Disorders (ASD). 

   more » « less
3. Optimization-based Task and Motion Planning under Signal Temporal Logic Specifications using Logic Network Flow

   Lin, Xuan; Ren, Jiming; Coogan, Samuel; Zhao, Ye (May 2025, IEEE International Conference on Robotics and Automation)

   This paper proposes an optimization-based task and motion planning framework, named “Logic Network Flow”, to integrate signal temporal logic (STL) specifications into efficient mixed-binary linear programmings. In this framework, temporal predicates are encoded as polyhedron constraints on each edge of the network flow, instead of as constraints between the nodes as in the traditional Logic Tree formulation. Synthesized with Dynamic Network Flows, Logic Network Flows render a tighter convex relaxation compared to Logic Trees derived from these STL specifications. Our formulation is evaluated on several multi-robot motion planning case studies. Empirical results demonstrate that our formulation outperforms Logic Tree formulation in terms of computation time for several planning problems. As the problem size scales up, our method still discovers better lower and upper bounds by exploring fewer number of nodes during the branch-andbound process, although this comes at the cost of increased computational load for each node when exploring branches. 

   more » « less
4. Biomechanics‐Based User‐Adaptive Variable Impedance Control for Enhanced Physical Human–Robot Interaction Using Bayesian Optimization

   https://doi.org/10.1002/aisy.202400333  

   Zahedi, Fatemeh; Lee, Hyunglae (September 2024, Advanced Intelligent Systems)

   This paper presents a biomechanics‐based, user‐adaptive variable impedance controller designed to enhance the performance of coupled human–robot systems during motion. The controller integrates the biomechanical characteristics of human limbs and dynamically adjusts the robotic impedance parameters—specifically damping, stiffness, and equilibrium trajectory—based on real‐time estimations of the user's intent and direction of motion. The primary goal is to minimize the energy expenditure of the coupled human–robot system while maintaining system passivity. To address uncertainties in human behavior and noisy observations, the controller employs Bayesian optimization combined with a Gaussian process. To validate the proposed approach, human experiments are conducted using a standard robotic arm manipulator. The results demonstrate that the controller eliminates the need for manual parameter tuning, a process that is typically time‐consuming. A comparative analysis against two variable impedance controllers without user‐adaptive parameter adjustments reveal significant benefits, with the controller improving combined performance metrics—such as accuracy, speed, user effort, and smoothness—by over 13%. Notably, all participants in the study preferred the optimized controller over the alternatives. These findings highlight the effectiveness of the biomechanics‐based, user‐adaptive variable impedance control approach and its potential to enhance physical human–robot interaction in various applications that involve repetitive or continuous motion. 

   more » « less
5. NAUTS: Negotiation for Adaptation to Unstructured Terrain Surfaces

   https://doi.org/10.1109/IROS47612.2022.9982207  

   Siva, Sriram; Wigness, Maggie; Rogers, John G.; Quang, Long; Zhang, Hao (October 2022, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS))

   When robots operate in real-world off-road environments with unstructured terrains, the ability to adapt their navigational policy is critical for effective and safe navigation. However, off-road terrains introduce several challenges to robot navigation, including dynamic obstacles and terrain uncertainty, leading to inefficient traversal or navigation failures. To address these challenges, we introduce a novel approach for adaptation by negotiation that enables a ground robot to adjust its navigational behaviors through a negotiation process. Our approach first learns prediction models for various navigational policies to function as a terrain-aware joint local controller and planner. Then, through a new negotiation process, our approach learns from various policies' interactions with the environment to agree on the optimal combination of policies in an online fashion to adapt robot navigation to unstructured off-road terrains on the fly. Additionally, we implement a new optimization algorithm that offers the optimal solution for robot negotiation in real-time during execution. Experimental results have validated that our method for adaptation by negotiation outperforms previous methods for robot navigation, especially over unseen and uncertain dynamic terrains. 

   more » « less