Publications

2026

1. IoTJ

   

   Delay-Aware Shared Control for Teleoperation Systems: Intent Trajectory Prediction Under Communication Latency

   Jinwei Liu, Pengfei Li, Yaqing Zhou, and 3 more authors

   IEEE Internet of Things Journal, 2026

   Abs DOI HTML

   Shared-control teleoperation systems, which combine human cognitive versatility and robotic precision, are essential for executing complex tasks in inaccessible environments. A critical challenge in such systems is accurately estimating the operator’s intent to ensure the robot’s assistive actions align with the operator’s goals. Traditional trajectory prediction methods estimate the robot’s future path as the operator’s intent. However, without accounting for communication delays, these methods predict the robot’s execution trajectory, which diverges from the operator’s intended trajectory due to the delays. To address this issue, we propose the delay-aware Robot Trajectron (DA-RT), which restores the causal relationship between observed commands and actions by leveraging temporally aligned data and a delay-conditioned attention pooling mechanism. This enables DA-RT to accurately estimate the operator’s intended trajectory under communication delays. Then, we integrate DA-RT with an artificial potential field based controller and a dynamic arbitration mechanism to form a delay-aware shared-control framework, which adjusts the level of assistance based on delay magnitude and the agreement between the operator’s command and the robot’s motion. In human-in-the-loop experiments with fifteen participants, our approach demonstrated significant improvements in both task success rate and efficiency, outperforming traditional methods.

2. IROS

   

   Legible Shared Autonomy: Implicit Communication of Robot Belief through Motion

   Jinwei Liu, Pengfei Li, Shaofeng Chen, and 2 more authors

   In IEEE/RSJ International Conference on Intelligent Robots and Systems, 2026

   Accepted

   Abs arXiv Code

   Shared autonomy systems combine user input with autonomous assistance to help users with motor impairments control robot arms for everyday manipulation tasks. However, traditional shared autonomy often moves efficiently but ambiguously toward inferred goals, preventing users from understanding the robot’s internal belief about their intent. We introduce legible shared autonomy, where robot motion simultaneously advances task execution and implicitly communicates which goal the robot has inferred. The method combines an action-level legibility metric with confidence-aware adaptive authority allocation, enabling assertive legible assistance when the robot is confident while preserving user authority under uncertainty. User studies in 2D simulation and physical six degree-of-freedom robot arm experiments demonstrate that legible shared autonomy improves users’ understanding of robot beliefs and reduces user control effort compared with standard shared autonomy.

3. ICGNC

   

   LSTM-MPC: Physically Feasible and Interpretable Trajectory Prediction

   Jinwei Liu, Pengfei Li, Qianqian Zhang, and 2 more authors

   In International Conference on Guidance, Navigation and Control, 2026

   Accepted

   Abs

   As transportation systems evolve toward mixed traffic environments, accurate trajectory prediction of surrounding human-driven vehicles is essential for the safe operation of autonomous driving systems. Existing deep learning approaches either directly regress future coordinates, producing kinematically infeasible outputs, or predict raw control sequences that remain semantically opaque. We propose LSTM-MPC, a hierarchical framework that reframes prediction as the estimation of latent Model Predictive Control (MPC) parameters. A long short-term memory (LSTM) encoder infers semantically meaningful target waypoints and cost matrices from historical observations; a differentiable MPC layer then solves a constrained optimal control problem over kinematic bicycle dynamics, yielding physically feasible trajectories by construction. The entire pipeline is trained end-to-end via backpropagation through the optimization layer. Experiments in the CARLA simulator demonstrate that LSTM-MPC outperforms existing methods in accuracy, eliminates kinematic constraint violations, and converges in fewer training epochs, while the inferred parameters provide interpretable representations of driver intent and individual driving style.

4. IFAC WC

   

   Human-AI Shared Control via Motor Knowledge Neuron Stimulation

   Jinwei Liu, Pengfei Li, Sibin Huang, and 2 more authors

   In IFAC World Congress, 2026

   Accepted

   Abs

   Neuron-level control offers an effective approach to enabling human-AI shared control without retraining pretrained policies. However, existing methods assume motor primitives are encoded by individual neurons, limiting control precision and robustness. We propose Motor Knowledge Neuron Stimulation (MKNS), which recognizes that motor primitives distribute across neuron assemblies. MKNS identifies these assemblies via frequency-domain analysis and trains compact neural stimulators through iterative data aggregation using only 1% of the original training data. Experiments validate MKNS effectiveness while revealing fundamental properties of motor knowledge: directional asymmetry, the necessity of distributed encoding, and cross-talk between primitives.