{"ID":3005058,"CreatedAt":"2026-06-03T03:09:48.883664427Z","UpdatedAt":"2026-06-05T07:50:16.0004273Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.03297","arxiv_id":"2606.03297","title":"SplitAdapter: Load-Aware Humanoid Loco-Manipulation via Factorized Adaptation","abstract":"Humanoid loco-manipulation requires stable whole-body control under varying object masses and pickup/placement heights. This becomes particularly challenging in sim-to-real transfer, where object-induced load variation and robot-side dynamics mismatch interact during physical contact. Existing history-based adapters often compress these factors into a single latent representation, which can weaken robustness under heavy-load manipulation. We propose \\textbf{SplitAdapter: Load-Aware Humanoid Loco-Manipulation via Factorized Adaptation}, which freezes a pretrained box manipulation policy and extends it with object/load and dynamics-aware context encoders trained with split world-model objectives, GRL-based cross-adversarial regularization, and hierarchical Feature-wise Linear Modulation (FiLM). In sim-to-sim experiments and real-world deployment, SplitAdapter improves Full-task success over the base policy and world-model FiLM baselines across object masses of $2$, $4$, and $6$ kg and pickup/placement heights of $0$, $30$, and $60$ cm, with the largest improvements under heavy-load conditions.","short_abstract":"Humanoid loco-manipulation requires stable whole-body control under varying object masses and pickup/placement heights. This becomes particularly challenging in sim-to-real transfer, where object-induced load variation and robot-side dynamics mismatch interact during physical contact. Existing history-based adapters of...","url_abs":"https://arxiv.org/abs/2606.03297","url_pdf":"https://arxiv.org/pdf/2606.03297v1","authors":"[\"Jeonguk Kang\",\"Hanbyel Cho\",\"Sanghyun Kang\",\"Donghan Koo\"]","published":"2026-06-02T08:10:49Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","has_code":false}