GUIDER—Global User Intent Dual-phase Estimation for Robots—tries to recognise what a teleoperator is working towards without requiring a predefined list of goals. It separates the journey to a work area from the subsequent manipulation, using scene information and human motion to maintain a changing belief about the intended target.
Why Intent Needs Two Levels
When a person drives a mobile manipulator towards a table, the immediate goal is a useful area, not yet necessarily a particular grasp. Once the robot is nearby, arm movement can distinguish between neighbouring objects. Treating both phases as one fixed target-selection problem loses that structure.
GUIDER first estimates likely navigation regions, then uses a local scene reconstruction to infer manipulation intent. This does not mean the robot reads a person’s thoughts: it ranks hypotheses from observable commands and geometry. Ambiguous movement or a deliberate change of goal should change that ranking.
From Navigation Evidence to Object Candidates
The navigation phase combines controller velocities with an occupancy-grid representation. A synergy map helps identify plausible work regions from the environment and commanded motion. Candidate areas are derived from the scene rather than supplied as a fixed operator-selected goal list.
After reaching the selected area, an autonomous multi-view scan constructs a local point cloud. Plane extraction and clustering organise the geometry, and cluster centroids provide prompts for instance segmentation. This is a bridge between three-dimensional structure and image-based object separation.
During manipulation, U2Net saliency supplies information about visually prominent regions, while FastSAM separates candidate objects. Geometric and grasp-related constraints help reject implausible interpretations. An object attracting visual attention is not necessarily reachable, graspable or intended; the movement evidence has to refine the initial scene-based ranking.
This explains the value of combining perception with motion. Geometry restricts what is physically plausible, while the operator’s trajectory provides evidence about which plausible target is currently relevant.
Understanding the Reported Metrics
The preprint evaluates 25 trials: five users performing five task variants in Isaac Sim. The journal article was published on 5 March 2026; the following numerical examples specifically refer to the documented preprint evaluation.
| Comparison | GUIDER | Baseline | Interpretation |
|---|---|---|---|
| Navigation median stability, T5 | 100% | 60.5% for BOIR | 39.5 percentage points higher |
| Manipulation median stability, T3 | 100% | 68.6% for Trajectron | 31.4 percentage points higher |
| Median remaining time at confident prediction, geometry-constrained manipulation | 23.6 s | 7.8 s | More advance warning before contact |
Stability concerns maintaining the correct interpretation over time, not merely producing a consistent answer. A consistently wrong target is not a successful stable prediction.
Remaining time measures how much of the task is left once a confident prediction is available. The 23.6-second result is roughly three times the 7.8-second warning interval. It is not evidence of three-times-faster computation: processing latency is a different quantity.
What This Enables—and What Was Not Tested
Earlier, persistent identification of an intended target could give an assistive controller time to prepare a useful movement or ask for confirmation. The inference system is therefore a potential input to shared autonomy, rather than proof that every subsequent assistance action will be helpful.
The reported trials do not evaluate a complete closed-loop intent-based intervention. Demonstrating better prediction and demonstrating better assisted task completion require different experiments. Five participants in simulation also cannot establish general performance across users, sensor conditions and physical workcells.
Numerical reproduction would need the same scenes, recordings, perception models, calibration, manually chosen parameters and baseline information. Replaying identical time-stamped commands through competing estimators would help separate algorithm differences from differences in the input, while retaining participant-level structure in the analysis.
Testing and Real-World Use
This could be tested by replaying matched navigation and arm trajectories with known target changes, measuring prediction correctness, stability and how early the intended target becomes clear. In remote handling, the resulting estimate could help an assistant prepare target-specific support while leaving acceptance and uncertain decisions with the operator.
Paper Versions
Read the full preprint with figures and evaluation details or the journal publication. The distinction between versions is retained so that the numerical examples can be checked against the exact source used here.