Learning Smooth and Robust Space Robotic Manipulation of Dynamic Target via Inter-frame Correlation

Siyi Lang; Hongyi Gao; Yingxin Zhang; Zihao Liu; Hanlin Dong; Zhaoke Ning; Zhiqiang Ma; Panfeng Huang

cs.ROMar 29, 2026

Learning Smooth and Robust Space Robotic Manipulation of Dynamic Target via Inter-frame Correlation

Authors: Siyi Lang, Hongyi Gao, Yingxin Zhang, Zihao Liu, Hanlin Dong, Zhaoke Ning, Zhiqiang Ma, Panfeng Huang

Organizations: Research Center for Intelligent Robotics, School of Astronautics, Northwestern Polytechnical University, Xi’an 710072, China · School of Automation, Northwestern Polytechnical University, Xi’an 710072, China · School of Aeronautics and Astronautics, Sichuan University, Chengdu 610065, China

Abstract

On-orbit servicing represents a critical frontier in future aerospace engineering, with the manipulation of dynamic non-cooperative targets serving as a key technology. In microgravity environments, objects are typically free-floating, lacking the support and frictional constraints found on Earth, which significantly escalates the complexity of tasks involving space robotic manipulation. Conventional planning and control-based methods are primarily limited to known, static scenarios and lack real-time responsiveness. To achieve precise robotic manipulation of dynamic targets in unknown and unstructured space environments, this letter proposes a data-driven space robotic manipulation approach that integrates historical temporal information and inter-frame correlation mechanisms. By exploiting the temporal correlation between historical and current frames, the system can effectively capture motion features within the scene, thereby producing stable and smooth manipulation trajectories for dynamic targets. To validate the effectiveness of the proposed method, we developed a ground-based experimental platform consisting of a PIPER X robotic arm and a dual-axis linear stage, which accurately simulates micro-gravity free-floating motion in a 2D plane.

Figures & tables

Fig. 1: Illustration of trajectory oscillation.

Fig. 2: Overview of the proposed network architecture. The top-left portion displays the CVAE encoder, which predicts the style latent variable $z$ representing task characteristics. The bottom-left portion integrates an inter-frame correlation network to extract key motion tokens by comparing consecutive visual frames. The right portion shows the CVAE decoder, which maps the current multi-modal perception data and latent variables into the final robotic action sequences.

Fig. 3: Schematic of the Inter-frame Correlation Network. The network processes spatio-temporal correlation information through two primary stages: the first stage involves cost volume calculation, encoding, and compression, transforming consecutive image features into cost volume semantic representations. The second stage implements a Spatial Self-Attention mechanism, utilizing intra-token, vertical, and horizontal self-attention blocks to enhance the network’s ability to capture global spatial dependencies within the cost maps.

Layer	Input Size	Kernel	Stride	Channel
Conv1 + ReLU	$15\times 20$	$6\times 6$	2	$d_{\text{embed}}/4$
Conv2 + ReLU	$7\times 10$	$6\times 6$	2	$d_{\text{embed}}/2$
Conv3	$3\times 5$	$6\times 6$	2	$d_{\text{embed}}$

TABLE I: Architecture of the CNN for cost volume Embedding.

Fig. 4: Overview of the ground-based experimental platform.

Fig. 6: This figure illustrates the multi-view visual feedback during manipulation. From left to right are the hand-eye camera view and two global field camera views.

Fig. 7: Radar chart comparing the performance of our method, the vanilla ACT, and DP across five scenarios.

Fig. 8: Motor torque profiles during a successful manipulation task. The gray dashed line indicates the moment of end-effector closure. It is observed that the motor torque increases immediately at this instant to provide the necessary constraint to bring the target to a halt.

Fig. 9: Comparison of trajectory clusters and divergence between the vanilla ACT (left) and our method (right). The bottom plot displays the real-time “average distance” curves, with the legend indicating the time-averaged mean distance for each method to quantify overall cluster divergence.

Method	Normal		Camera Occlusion		Target Occlusion		Target Maneuver		Low-light
Method	MASD( $\downarrow$ )	Jerk( $\downarrow$ )	MASD( $\downarrow$ )	Jerk( $\downarrow$ )	MASD( $\downarrow$ )	Jerk( $\downarrow$ )	MASD( $\downarrow$ )	Jerk( $\downarrow$ )	MASD( $\downarrow$ )	Jerk( $\downarrow$ )
DP	13.73	37.99	14.22	36.86	16.07	37.98	14.79	36.21	15.88	38.04
Vanilla ACT	0.231	8.87	0.236	9.26	0.269	11.03	0.241	8.26	0.259	10.42
Ours	0.167	5.71	0.199	6.48	0.181	6.33	0.167	5.86	0.204	7.64

Fig. 10: Quantitative comparison of policy oscillations.

Fig. 11: Monte Carlo experiment results showing the success rates of the robotic arm from various initial positions.

Fig. 12: Heat map illustrating the success rates of the robotic manipulation across different initial target positions in the grayscale testing.

Space Robotics

Space robotics develops robots and autonomy for exploring, assembling, and maintaining spacecraft and planetary environments.

See all 71 papers

A Dexterous and Compliant Gripper With Soft Hydraulic Actuation for Microgravity Manipulation
May 18, 2026William Su, Jordan Kam, Yixiao Wang +1Dexterous Manipulation Space Robotics
Aerospace Engineering Program, University of California, Berkeley, Berkeley, CA 94720, USA. · Department of Mechanical Engineering, University of California, Berkeley, Berkeley, CA 94720, USA. · Department of Mechanical Engineering, National University of Singapore, Singapore 117575.
Validation of Space Robotics in Underwater Environments via Disturbance Robustness Equivalency
Feb 28, 2026Joris Verhagen, Elias Krantz, Chelsea Sidrane +9Space Robotics
Division of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, Sweden. · School of Engineering Sciences, KTH Royal Institute of Technology, Stockholm, Sweden. · Division of Decision and Control Systems, KTH Royal Institute of Technology, Stockholm, Sweden. +1
Path Planning and Reinforcement Learning-Driven Control of On-Orbit Free-Flying Multi-Arm Robots
Mar 24, 2026Álvaro Belmonte-Baeza, José Luis Ramón, Leonard Felicetti +2Robotic Control Space Robotics
University of Alicante, Spain · Cranfield University, UK

May 18, 2026J/K move · Enter open · S save

A Dexterous and Compliant Gripper With Soft Hydraulic Actuation for Microgravity Manipulation

William Su, Jordan Kam, Yixiao Wang, Jianshu Zhou

Aerospace Engineering Program, University of California, Berkeley, Berkeley, CA 94720, USA. · Department of Mechanical Engineering, University of California, Berkeley, Berkeley, CA 94720, USA. · Department of Mechanical Engineering, National University of Singapore, Singapore 117575.

Dexterous Manipulation Space Robotics Robotics Robotic Manipulation Soft Robotics

Open paper AskPDF arXiv

Astrobee's existing one-degree-of-freedom (DOF) underactuated compliant claw gripper enables perching on the International Space Station (ISS), but provides limited capability for continuous dexterous manipulation. More complex microgravity tasks require an end-effector that can maintain stable contact while limiting disturbance to the free-flying base, since contact forces directly couple into base motion. This article presents the integration of DexCoHand, a dexterous and compliant two-finger, 6-DOF gripper, with the Astrobee free-flying robot for microgravity manipulation. The system is evaluated in MuJoCo using Astrobee's standard handrail perching sequence, including approach, perching, and subsequent pan and tilt motions. Compared with Astrobee's existing gripper, DexCoHand preserves the commanded pan and tilt motions while reducing unintended cross-axis base motion. Hardware experiments on Earth further demonstrate DexCoHand's dexterous manipulation capabilities and its potential for more adaptable intelligent manipulation tasks.

Abstract

Space Robotics

Explore similar work

A Dexterous and Compliant Gripper With Soft Hydraulic Actuation for Microgravity Manipulation

Validation of Space Robotics in Underwater Environments via Disturbance Robustness Equivalency

Path Planning and Reinforcement Learning-Driven Control of On-Orbit Free-Flying Multi-Arm Robots