Transformer-Based Warm-Starting for Feasible and Optimal Terminal Approach to Tumbling Objects with Space Manipulators
arXiv:2606.17317v1 Announce Type: cross Abstract: Real-time trajectory generation for on-orbit robotic servicing is challenging due to the nonlinear coupling between spacecraft bus motion, manipulator dynamics, visibility cone, and trajectory-level safety constraints. This paper studies learning-based warm-starting for sequential convex programming (SCP) in the terminal approach of a space manipulator toward a tumbling target. The proposed framework decomposes the problem into a system center-of-mass translational planning stage and a coupled attitude--manipulator torque-allocation stage, and
The increasing density of space assets and the strategic importance of on-orbit servicing and debris removal are driving significant research and development in autonomous space robotics.
This development represents a crucial step towards robust, autonomous robotic capabilities in space, enabling complex tasks like debris removal, satellite repair, and in-situ resource utilization, thereby securing orbital infrastructure.
The ability to reliably and efficiently perform autonomous terminal approach to tumbling objects with space manipulators changes the operational paradigm for space-based servicing and maintenance, reducing reliance on direct human control.
- · Space agencies
- · Satellite operators
- · In-space servicing companies
- · Defence contractors
- · Operators of legacy, non-servicing satellites
- · Companies relying on manual space operations
Increased operational safety and efficiency for on-orbit repairs and debris mitigation.
Expansion of the viable applications for space robotics, including on-orbit assembly and manufacturing.
Potential for a more resilient and sustainable space economy due to enhanced in-space capabilities and reduced collision risks.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI