FlexWorm: Primitive-augmented Hybrid Contact-motion Planning for Suction-based Multi-segment Deformable Robots

Zili Tang; Tiecheng Guo; Qinyue Zhang; Meng Guo

cs.ROAug 17, 2026

FlexWorm: Primitive-augmented Hybrid Contact-motion Planning for Suction-based Multi-segment Deformable Robots

Authors: Zili Tang, Tiecheng Guo, Qinyue Zhang, Meng Guo

Organizations: School of Advanced Manufacturing and Robotics, Peking University, Beijing 100871, China

Abstract

Multi-segment suction-based soft robots are promising for inspection and maintenance in confined or fragile environments, but existing approaches still depend heavily on manually designed gaits and environment-specific motion scripts. This work presents a planning framework for serial multi-segment soft robots with deformable body segments and boundary suction pads. The formulation targets full 3D navigation on complex surfaces and explicitly handles discrete adhesion switching and continuous body deformation under geometric, collision, and quasi-static feasibility constraints, while remaining agnostic to the specific actuation realization used to produce segment deformation. Its core, block-wise IK hybrid search (IKHS), performs best-first search over feasible adhesion transitions while solving inverse kinematics only on induced free blocks. On top of IKHS, primitive-augmented hybrid search (PaHS) uses a learned observation--primitive embedding to retrieve short validated motion segments for fast local proposal, with fallback to standard IKHS branching when retrieval fails. In simulation, the framework consistently outperforms controlled baselines in planning success, transition quality, and efficiency across diverse terrains. PaHS matches IKHS in success rate while substantially reducing planning time. Repeated hardware experiments on a pneumatic multi-segment soft robot further demonstrate executability and online recovery under actuation and adhesion uncertainty.

Figures & tables

Fig. 1: PaHS plans over discrete adhesion modes and continuous body deformation for multi-segment soft robots on diverse 3D terrain transitions.

Fig. 2: Multi-segment soft robot with rigid links, four-chamber deformable segments, and independently switched suction pads, composed into the hybrid state $(\mathbf{X}^{h},\mathbf{U}^{h},\mathbf{Z}^{h})$ . Links are indexed from tail to head.

Fig. 3: Examples of the guiding surface paths in three test scenarios.

Fig. 4: Schematic of the block-wise IK hybrid search (IKHS), including five main steps ( top ); the block decomposition and propagation ( bottom ).

Fig. 5: Unified overview of IKHS and PaHS. Offline IKHS rollouts generate validated short-horizon primitives. Online, IKHS performs best-first hybrid search with block-wise IK, while PaHS first attempts primitive-based expansion and falls back to IKHS when needed.

Fig. 6: Different embeddings for primitives: random (left) and learned (right), compared by their alignment with primitive distances.

Fig. 7: Representative simulation scenarios and planned trajectories. The benchmark covers cluttered terrain, strong curvature, and multiple surface transitions.

Module	Parameters
Guide	$(w_{\ell},w_{\texttt{lift}},w_{\texttt{sharp}},w_{\texttt{n}},w_{\texttt{b}},w_{\texttt{nc}})=(1,1,10,1,2,30)$
IK	Target weights $(w_{\mathrm{nd}},w_{\mathrm{td}},w_{\mathrm{no}},w_{\mathrm{o}})=(10^{4},10^{2},10^{2},10^{-1})$ ; deformation weight $w_{d}=10^{-2}$ ; max. $40$ iter./target
Expansion	$\leq 32$ targets/free block; top- $K$ pruning, $K=3$ ; beam $3$
IKHS score	$w_{\texttt{lat}}=0.4$ ; $w_{\texttt{d}}^{h}=0.1\alpha_{\texttt{p}}$ , $\alpha_{\texttt{p}}\in[0.1,1.0]$ ; $w_{\texttt{e}}=0.05$ ; ext./bend $(0.2,1.0)$
PaHS	$H_{\texttt{p}}=4$ ; retrieval $K=50$ ; $d=16$
Training	batch $256$ ; lr $10^{-3}$ ; decay $10^{-5}$ ; $200$ epochs; hard-pair sampling

TABLE I: Main implementation parameters.

Fig. 8: Effect of library size and expansion budget on the retrieval hit rate and planning acceleration, within three different scenarios.

	Seen (avg. 3 scen.)		Unseen
Encoder	PT (s)	Hit (%)	PT (s)	Hit (%)
Metric ( ours )	2.64	87.9	2.88	80.5
Random	3.25	77.5	4.09	64.3
Pooled PCA	5.17	62.1	4.29	58.6

TABLE II: Metric-learning ablation for primitive retrieval.

Fig. 9: Illustration of how the IK-feasible (in blue) and infeasible (in red) regions change drastically under different guiding paths (black line).

Method	Succ. (/20)			PT (s)			ES			DC
Method	S1	S2	S3	S1	S2	S3	S1	S2	S3	S1	S2	S3
PaHS	20	20	20	1.7	1.0	1.8	51	35	45	68	42	84
IKHS	20	20	20	20.4	11.9	15.6	64	47	56	71	43	80
PaHS-NF	10	18	11	100.6	20.8	90.6	125	51	112	130	56	128
PWTO	9	12	10	129.2	98.6	117.7	148	118	137	180	139	178
RPR	12	15	3	80.6	50.6	170.1	109	76	174	126	83	174

TABLE III: Comparison with Baselines.

Fig. 10: Failure cases for the baseline RPR : without IK refinement, small perturbations can turn a feasible wall-transition plan (green) into an infeasible one (red) that violates the suction constraint.

Fig. 11: Resulting trajectories under baselines PaHS , PWTO , and DBS .

Fig. 12: Snapshots during the planar navigation and the $45^{\circ}$ -slope transition, together with the corresponding closed-loop tracking and pressure commands.

Panel of Figure 16 — Fig. S1: Projected quasi-static samples used to construct $\mathcal{S}_{\texttt{D}}(\gamma)$ for $\gamma=0^{\circ}$ and $\gamma=120^{\circ}$ . For visualization, the two-dimensional curvature vector is projected to its magnitude $\kappa\triangleq\|\bm{\kappa}\|_{2}$ ; the planner retains the full vector $\bm{\kappa}\in\mathbb{R}^{2}$ . The panels show the $(L,\kappa)$ , $(L,\overline{M})$ , and $(\kappa,\overline{M})$ projections. The red curves indicate projected conservative bounds where shown.

Panel of Figure 17 — Fig. S2: Three-dimensional magnitude projections of the fitted gravity-conditioned feasible sets for $\gamma=0^{\circ}$ and $\gamma=120^{\circ}$ , using $\kappa=\|\bm{\kappa}\|_{2}$ for visualization. The planner-side feasible set itself is represented in $(\overline{M},L,\bm{\kappa})$ space.

Fig. S3: PaHS primitive-retrieval model and training protocol. The observation tower embeds the local depth, proprioception, gravity, and guide-window inputs, while the action tower embeds validated IKHS primitive continuations. Retrieved primitives are replayed, refined, and accepted after validation.

Fig. S4: Effect of deformation regularization in numerical IK. The upper panels show representative full-robot solutions and per-segment deformation contributions $\eta_{i}$ ; the middle panels show paired multi-target solution families; the lower panels show per-target deformation contributions.

Fig. S5: Planning-level deformation ablation in the curve scenario. Global ghost trajectories and matched follow-view frames are shown above the raw deformation and maximum-curvature traces.

Fig. S6: Illustration of the hardware execution difficulty in the $45^{\circ}$ slope transition. The figure summarizes the posture-dependent load moment, limited execution margin near $\mathcal{S}_{\texttt{D}}(\gamma)$ , and delay and uncertainty sources in the hardware feedback loop.

Contact-Aware Motion Planning

See all 13 papers

THREAD: Trajectory Planning for Hybrid Rigid-Soft Manipulators with Environment-Aware Diffusion
Jun 19, 2026Shivani Kamtikar, Pranav Asthana, Naveen Kumar Uppalapati +2Constrained Motion Planning Trajectory Generation
University of Illinois Urbana-Champaign · University of Maryland College Park
Unified Complementarity-Based Contact Modeling and Planning for Soft Robots
Feb 24, 2026Milad Azizkhani, Yue ChenSoft Robotics Contact-Rich Robotic Manipulation
Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA, USA · Institute for Robotics and Intelligent Machines (IRIM), Georgia Institute of Technology, Atlanta, GA, USA · Coulter Department of Biomedical Engineering (Georgia Tech and Emory University), Georgia Institute of Technology, Atlanta, GA, USA
SWIM: Vision-Language-Grounded Soft Whole-Body Interactive Manipulation
Sep 15, 2026Tingcong Liu, Aye Phyu Phyu Aung, Junjie Xiong +4Language-Conditioned Robot Manipulation Whole-Body Robotic Manipulation
Nanyang Technological University, Singapore · Institute of Advanced Intelligence and Computing, A*STAR, Singapore · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates +1

Jun 19, 2026J/K move · Enter open · S save

THREAD: Trajectory Planning for Hybrid Rigid-Soft Manipulators with Environment-Aware Diffusion

Shivani Kamtikar, Pranav Asthana, Naveen Kumar Uppalapati, Girish Krishnan+1

University of Illinois Urbana-Champaign · University of Maryland College Park

Constrained Motion Planning Trajectory Generation Diffusion-Based Planning Robotic Manipulation Robot Motion Planning Soft Robotics+1

Open paper AskPDF arXiv

Manipulation in confined environments, such as threading a manipulator through narrow apertures, remains a fundamental challenge, especially for conventional rigid robots. Hybrid rigid-soft manipulators offer promise but face two compounding planning challenges: backbone shapes feasible in free space become infeasible under environmental contact, and planning rigid and soft segments independently ignores their kinematic coupling. We present THREAD, the first diffusion-based trajectory planner for hybrid manipulation, learning a generative prior over physically realizable backbone trajectories conditioned on local environment geometry, with physics-inspired losses encoding curvature, smoothness, and collision constraints jointly across both segments. Trained in simulation, THREAD achieves 92.4% task success with 5x fewer collisions than the strongest baseline. We show cross-embodiment real-world transfer with minimal online updates, successfully threading through apertures as small as 1.3x the soft segment diameter.

Abstract

Contact-Aware Motion Planning

Explore similar work

THREAD: Trajectory Planning for Hybrid Rigid-Soft Manipulators with Environment-Aware Diffusion

Unified Complementarity-Based Contact Modeling and Planning for Soft Robots

SWIM: Vision-Language-Grounded Soft Whole-Body Interactive Manipulation