Changes in End Effector Trajectory Jitter Amplitude under the Interaction of Lerobot Diffusion Policy Denoising Steps and SLAM Loopback Frequency
Main Article Content
Abstract
This study investigates the interaction between the number of denoising steps in a LeRobot Diffusion Policy and the frequency of Simultaneous Localization and Mapping loop-closure corrections on end-effector trajectory jitter in mobile manipulation systems. A controlled experimental framework was established in which the robotic arm motion path and disturbance magnitude were held constant while denoising-step levels and loop-closure frequencies were independently varied. End-effector trajectories were collected in Cartesian space, and high-frequency jitter components were extracted to quantify trajectory instability. Two-way analysis of variance was employed to evaluate the main effects and interaction effect of the two factors. The results reveal a statistically significant interaction effect, indicating that the effectiveness of denoising-step adjustment depends strongly on loop-closure frequency. Under low-frequency disturbance conditions, increasing the number of denoising steps reduced the normalized jitter amplitude to approximately 47% of the baseline level. However, under high-frequency disturbance conditions, the same adjustment reduced the normalized jitter amplitude only to approximately 83% of the baseline level, demonstrating a substantial decline in suppression effectiveness. Frequency-domain analysis further shows that dense loop-closure disturbances can induce delayed compensation and low-frequency energy accumulation when excessive smoothing is applied, thereby limiting the benefits of additional denoising steps. These findings reveal a parameter dependency boundary between policy smoothing strength and disturbance frequency and provide a quantitative basis for coordinated configuration of perception and control modules, contributing to improved trajectory smoothness and operational stability in mobile manipulation robots operating in dynamic environments.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
W. Hao, P. Wang, C. Ni, W. Huangfu, Z. Liu, and K. Qi, “Loop closure detection based on image feature matching and motion trajectory similarity for mobile robot,” Applied Intelligence, vol. 55, no. 7, pp. 447–455, 2025, doi: 10.1007/s10489-024-05874-4.
C. Chi, Z. Xu, S. Feng, E. Cousineau, Y. Du, B. Burchfiel, et al., “Diffusion policy: Visuomotor policy learning via action diffusion,” The International Journal of Robotics Research, vol. 44, no. 10–11, pp. 1684–1704, 2025, doi: 10.1177/02783649241273668.
C. Yu, Z. Chao, H. Xie, Y. Hua, and W. Wu, “An Enhanced Multi-Sensor Simultaneous Localization and Mapping (SLAM) Framework with Coarse-to-Fine Loop Closure Detection Based on a Tightly Coupled Error State Iterative Kalman Filter,” Robotics, vol. 13, no. 1, pp. 2–11, 2023, doi: 10.3390/robotics13010002.
Y. Cai, Y. Ou, and T. Qin, “Improving SLAM techniques with integrated multi-sensor fusion for 3D reconstruction,” Sensors, vol. 24, no. 7, pp. 2033–2039, 2024, doi: 10.3390/s24072033.
S. Arshad and G. W. Kim, “Role of deep learning in loop closure detection for visual and lidar slam: A survey,” Sensors, vol. 21, no. 4, pp. 1243–1250, 2021, doi: 10.3390/s21041243.
C. E. Denniston, Y. Chang, A. Reinke, K. Ebadi, G. S. Sukhatme, and L. Carlone, “Loop closure priorityization for efficient and scalable multi-robot SLAM,” IEEE Robotics and Automation Letters, vol. 7, no. 4, pp. 9651–9658, 2022, doi: 10.1109/LRA.2022.3191156.
J. Carvalho, A. T. Le, P. Kicki, D. Koert, and J. Peters, “Motion planning diffusion: Learning and adapting robot motion planning with diffusion models,” IEEE Transactions on Robotics, vol. 41, no. 1, pp. 4881–4901, 2025, doi: 10.1109/TRO.2025.3593109.
H. Qiu, Z. Chen, Z. Wang, Y. He, M. Xia, and Z. Liu, “FreeTraj: Tuning-Free Trajectory Control via Noise Guided Video Diffusion,” International Journal of Computer Vision, vol. 134, no. 4, pp. 165–172, 2026, doi: 10.1007/s11263-026-02732-3.
X. Shi, Y. Hu, and J. Jin, “FRMD: fast robot motion diffusion via trajectory-level consistency distillation,” Frontiers in Robotics and AI, vol. 13, no. 1, pp. 1751688–1751694, 2026, doi: 10.3389/frobt.2026.1751688.
H. Ding, N. Jaquier, J. Peters, and L. Rozo, “Fast and robust visuomotor riemannian flow matching policy,” IEEE Transactions on robotics, vol. 41, no. 1, pp. 5327–5343, 2025, doi: 10.1109/TRO.2025.3601293.
J. Zhu, H. Li, and T. Zhang, “Camera, LiDAR, and IMU based multi-sensor fusion SLAM: A survey,” Tsinghua Science and Technology, vol. 29, no. 2, pp. 415–429, 2023.
T. Xu, M. Chen, and J. Liu, “TKO-SLAM: Visual SLAM algorithm based on time-delay feature regression and keyframe pose optimization,” Journal of Field Robotics, vol. 41, no. 6, pp. 1960–1983, 2024, doi: 10.1002/rob.22357.
Y. Lian, X. Xiao, J. Zhang, L. Jin, J. Yu, and Z. Sun, “Neural dynamics for cooperative motion control of omnidirectional mobile manipulators in the presence of noises: A distributed approach,” IEEE/CAA Journal of Automatica Sinica, vol. 11, no. 7, pp. 1605–1620, 2024, doi: 10.1109/JAS.2024.124425.
R. Wolf, Y. Shi, S. Liu, and R. Rayyes, “Diffusion models for robotic manipulation: A survey,” Frontiers in Robotics and AI, vol. 12, no. 1, pp. 1606247–1606254, 2025, doi: 10.3389/frobt.2025.1606247.
C. Pan, Z. Yi, G. Shi, and G. Qu, “Model-based diffusion for trajectory optimization,” Advances in Neural Information Processing Systems, vol. 37, no. 1, pp. 57914–57943, 2024, doi: 10.52202/079017-1846.
S. Zheng, J. Wang, C. Rizos, W. Ding, and A. EI-Mowafy, “Simultaneous localization and mapping (slam) for autonomous driving: Concept and analysis,” Remote Sensing, vol. 15, no. 4, pp. 1156–1162, 2023, doi: 10.3390/rs15041156.
X. Jiang, L. Zhu, J. Liu, and A. Song, “A SLAM-based 6DoF controller with smooth auto-calibration for virtual reality,” The Visual Computer, vol. 39, no. 9, pp. 3873–3886, 2023, doi: 10.1007/s00371-022-02530-1.
M. Iqbal, R. A. M. Qureshi, and G. Abbas, “SIMULATING THE TIME-VARYING PARAMETERS OF ROBOTS IN PERFORMING THE COMPLEX SEQUENTIAL TASKS,” Pakistan Journal of Scientific Research, vol. 4, no. 1, pp. 93–104, 2024, doi: 10.57041/vol4iss1pp93-104.
C. Li, Z. Liu, L. Li, Z. Ji, C. Li, J. Liang, et al., “Improved PPO Optimization for Robotic Arm Grasping Trajectory Planning and Real-Robot Migration,” Sensors, vol. 25, no. 17, pp. 5253–5260, 2025, doi: 10.3390/s25175253.
Y. Guo, Y. Hu, J. Zhang, et al., “Prediction with action: Visual policy learning via joint denoising process,” Advances in Neural Information Processing Systems, vol. 37, no. 1, pp. 112386–112410, 2024, doi: 10.52202/079017-3570.
Y. Wang, Y. Tian, J. Chen, K. Xu, and X. Ding, “A survey of visual SLAM in dynamic environment: The evolution from geometric to semantic approaches,” IEEE Transactions on Instrumentation and Measurement, vol. 73, no. 1, pp. 1–21, 2024, doi: 10.1109/TIM.2024.3420374.
K. Kawaharazuka, J. Oh, J. Yamada, et al., “Vision-language-action models for robotics: A review towards real-world applications,” IEEE Access, vol. 13, no. 1, pp. 162467–162504, 2025, doi: 10.1109/ACCESS.2025.3609980.
I. Jebellat and I. Sharf, “Motion planners for path or waypoint following and end-effector sway damping with dynamic programming,” IEEE Transactions on Automation Science and Engineering, vol. 22, no. 1, pp. 8439–8452, 2024, doi: 10.1109/TASE.2024.3486040.
M. Wang, S. Lyu, Q. Liu, Z. Yang, K. Guo, and X. Yu, “Precise end-effector control for an aerial manipulator under composite disturbances: Theory and experiments,” IEEE Transactions on Automation Science and Engineering, vol. 22, no. 1, pp. 4006–4021, 2024, doi: 10.1109/TASE.2024.3406754.
H. Pan, D. Liu, J. Ren, T. Huang, and H. Yang, “LiDAR-IMU tightly-coupled SLAM method based on IEKF and loop closure detection,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 17, no. 1, pp. 6986–7001, 2024, doi: 10.1109/JSTARS.2024.3357536.
D. C. Hoang, J. A. Stork, and T. Stoyanov, “Voting and attention-based pose relation learning for object pose estimation from 3D point clouds,” IEEE Robotics and Automation Letters, vol. 7, no. 4, pp. 8980–8987, 2022, doi: 10.1109/LRA.2022.3189158.
R. Kranthi and Vasundhara, “A robust adaptive filter for diffusion strategy-based distributed active noise control,” IETE Journal of Research, vol. 70, no. 5, pp. 5066–5080, 2024, doi: 10.1080/03772063.2023.2222099.
M. B. Kadri, S. A. Khatri, and S. Yousuf, “Trajectory Tracking Control of a Planar Robotic Arm Using Inverse Dynamics and Fuzzy Gain Scheduling: Simulation and Experimental Validation,” IEEE Access, vol. 13, no. 1, pp. 186736–186759, 2025, doi: 10.1109/ACCESS.2025.3626418.
Q. Zhang, S. Feng, S. Chen, W. Teng, and Y. Qi, “Motion In-Betweening via Frequency-Domain Diffusion Model,” Computers, Materials, & Con-tinua, vol. 86, no. 1, pp. 1–9, 2026, doi: 10.32604/cmc.2025.068247.
S. Sakhrieh, A. Singh, J. Mounsef, B. Arain, and N. Maalouf, “VIO-GO: optimizing event-based SLAM parameters for robust performance in high dynamic range scenarios,” Frontiers in Robotics and AI, vol. 12, no. 1, pp. 1541017–1541024, 2025, doi: 10.3389/frobt.2025.1541017.
F. Bjelonic, A. Sachtler, A. Albu-Schäffer, and C. D. Santina, “Experimental closed-loop excitation of nonlinear normal modes on an elastic industrial robot,” IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 1689–1696, 2022, doi: 10.1109/LRA.2022.3141156.
F. A. C. Alegria, “Contribution of jitter and phase noise to the precision of sinusoidal amplitude estimation using coherent sampling,” Sci, vol. 7, no. 2, pp. 44–53, 2025, doi: 10.3390/sci7020044.
B. Wang, Y. Peng, H. Jin, and J. Zhao, “Reciprocal Neural State– Disturbance Observer for Model-Free Trajectory Tracking of Robotic Manipulators,” Mathematics, vol. 14, no. 6, pp. 983–991, 2026, doi: 10.3390/math14060983.
S. Yin, Z. Shi, Y. Liu, G. Xue, and H. You, “Adaptive Non-Singular terminal sliding mode trajectory tracking control of robotic manipulators based on disturbance observer under unknown Time-Varying disturbance,” Processes, vol. 13, no. 1, pp. 266–271, 2025, doi: 10.3390/pr13010266.
S. Bonnini, M. Borghesi, G. Piscopo, and M. Giacalone, “A Non-Parametric Test for a Two-Way Analysis of Variance,” Mathematics, vol. 13, no. 7, pp. 1131–1138, 2025, doi: 10.3390/math13071131.