SIMPNet: Spatial-Informed
Motion Planning Network

1 J. Mike Walker '66 Department of Mechanical Engineering, Texas A&M University 2 Zachry Department of Civil and Environmental Engineering, Texas A&M University
IEEE Robotics and Automation Letters
SIMPNet sampling heuristic overview

Method Overview. SIMPNet is a neural informed sampler for sampling-based motion planning. It represents the manipulator kinematic chain as a graph, embeds workspace observations, and uses cross-attention to generate spatially informed configuration-space samples for bidirectional planning.

Abstract

Robotic manipulators require fast and efficient motion planners to operate in cluttered environments. Sampling-based planners can struggle in high-dimensional configuration spaces because uniform or hand-crafted sampling heuristics often require many collision checks. SIMPNet addresses this limitation with a stochastic graph neural network sampling heuristic. The method encodes the manipulator's kinematic structure as a graph and uses cross-attention to condition configuration-space sampling on workspace embeddings. Experiments with a UR5e manipulator in simple and complex workspaces show that SIMPNet improves planning efficiency and remains competitive with sampling-based and neural planning baselines.

Highlights

Graph-aware sampling for faster manipulator motion planning.

SIMPNet keeps the sampling-based planner structure, but replaces uninformed sampling with a learned stochastic heuristic that is aware of robot kinematics and workspace geometry.

Graph Sampling

Encodes the UR5e kinematic chain as a graph for spatially informed sample generation.

Cross-Attention

Injects workspace embeddings into configuration-space sampling.

0.67s

planning time in the unseen simple environment benchmark.

97%

success rate in the unseen simple environment benchmark.

Method

Method

Spatial information guides sampling inside a classical planner.

SIMPNet learns a stochastic sampling heuristic that proposes the next configuration using the current state, goal state, robot graph features, and workspace embedding.

qnew = Heuristic(qa, qb, xa, xb, oenv)
1

Build Robot Graph

Represent joints and links as graph nodes and edges that follow the manipulator kinematic chain.

2

Fuse Workspace Context

Use cross-attention to condition graph features on the workspace embedding.

3

Plan with Informed Samples

Generate stochastic samples inside a bidirectional sampling-based planner.

UR5e graph construction

Graph Construction. The manipulator's kinematic structure is encoded as a graph, allowing message passing over robot joints.

Simple and complex SIMPNet environments

Evaluation Environments. SIMPNet is trained and evaluated in simple and complex workspaces.

Results

We compare SIMPNet with classical sampling-based planners and neural informed samplers across seen and unseen simple and complex environments. The interactive chart reports planning time, planning cost, and success rate from the published RA-L paper. Figure 6 from the paper is not reproduced here as a separate image; its comparison is represented through the recoverable table values below.

Real-world SIMPNet planning comparison

Planning Example. Qualitative comparison of SIMPNet with benchmark planners in a complex workspace.

Ablations

We summarize two ablations from the paper: removing forward-kinematics information from the graph features and evaluating SIMPNet under different obstacle counts.

Planning Videos

Bi-RRT (x8)

IRRT* (x4)

MPNet (x4)

SIMPNet (x4)

BibTeX

@article{soleymanzadeh2025simpnet,
  title     = {SIMPNet: Spatial-Informed Motion Planning Network},
  author    = {Soleymanzadeh, Davood and Liang, Xiao and Zheng, Minghui},
  journal   = {IEEE Robotics and Automation Letters},
  year      = {2025},
  publisher = {IEEE}
}