Chapter 9: Slip and Shear — Reacting Before the Grasp Fails

Overview

A grasp usually fails before the object visibly falls. The warning signs appear first in tactile signals: normal force decreases, shear force approaches the friction-cone boundary, the contact centroid drifts, or high-frequency vibration emerges. Slip-based control is the reflex layer that reacts before the grasp fails.

After reading this chapter, you should be able to... - Distinguish gross slip, incipient slip, and micro slip. - Explain how normal and shear force define a slip margin. - Describe why internal-force control matters in multi-finger grasps. - Design a division of labor between tactile reflexes and high-level policies.

9.1 Why Slip Is the First Practical Use of Tactile Control

Vision detects slip after the object has moved. Tactile sensing can detect the precursor: shear deformation at the contact patch, pressure-center drift, or vibration. That makes slip reflex the most direct application of tactile sensing to control.

A basic loop is:

1. estimate normal and tangential force at each contact;
2. construct a friction cone or friction pyramid using a friction estimate;
3. increase grip force when tangential force approaches the limit;
4. trigger a fast reflex when the contact patch moves or vibration appears;
5. reduce force when the object is fragile or deformation is detected.

This classical idea is still central in manufacturing. Cosmetic containers, thin films, caps, brushes, and sponges vary in surface material and friction. Over-grasping damages products; under-grasping drops them.

9.2 Shear Is Directional Contact Information

Normal force says whether the finger is pressing. Shear force says where the object is trying to move. In in-hand manipulation, shear is often the more useful signal. The controller must prevent accidental slip while sometimes creating intentional sliding or rolling.

Shear-aware grasp control enables questions that normal force alone cannot answer. If one finger's shear grows upward while another grows in the opposite direction, the object may be rotating inside the hand. This is especially useful when object pose is partially occluded.

9.3 Internal-Force Control

In a multi-finger grasp, the forces applied by the fingers create external wrench and internal force. Internal force does not move the object; it holds the contact set together. If it is too small, slip occurs. If it is too large, the object deforms or the actuators saturate.

Tactile internal-force control aims to:

• keep each normal force above the minimum stable level;
• avoid pushing one finger to the friction-cone boundary;
• separate object-moving wrench from object-holding internal wrench;
• redistribute force before one finger is released for regrasping.

The last point is central to sequential multi-object grasping. Before a finger is freed for the next object, tactile feedback must verify that the remaining contacts can support the first object.

9.4 Reflex Layer vs Policy Layer

Slip control should mostly live below the high-level policy. A 30 Hz vision-language policy may notice slip too late. A 500-1000 Hz tactile reflex can adjust grip immediately, while the high-level policy decides whether to regrasp, slow down, or change the task plan.

Sharpa's CraftNet framing of reflex intelligence as a fast System 0 points in the same direction ^[4]. Touch is a modality that needs a faster loop than language-level reasoning.

9.5 Sensor-Specific Slip Representations

The control question is therefore not simply which sensor is best. It is which slip feature can be obtained reliably at the rate required by the controller.

Summary

Slip and shear are the most practical entry point for tactile control. In-hand manipulation and multi-contact grasping both require maintaining some contacts while intentionally moving others. Tactile reflexes prevent drops, internal-force control redistributes load, and high-level policies decide how to recover or transition.

Manufacturing-Cell Checkpoint

Slip control is more precise than simply avoiding drops. Too little force causes failure, but too much force dents packages, deforms tubes, or damages labels. A tactile controller should log slip margin, normal-force reserve, shear direction, and grip-force increments rather than only a binary slip event. Because friction changes with contamination, packaging material, label position, and humidity, slip logs should be tied to SKU and cell conditions.

A production stack separates fast reflexes from slower policy updates. A 200-1000 Hz loop reacts to force derivatives and shear spikes. The higher-level policy then looks for SKU or grasp candidates that repeatedly require correction and updates the planner. In this form tactile sensing becomes part of the manufacturing data flywheel, not just a safety accessory.

Operational Reading Note

The practical value of this chapter is not only the concept of slip and shear control; it is the set of engineering decisions that the concept changes. A deployable robot-hand project should start by asking what state becomes observable after this chapter is applied. The answer should be concrete: contact existence, contact patch, normal force, shear direction, slip margin, object pose, task phase, operator override, or product-damage risk. If a variable cannot be logged or consumed by a controller, it remains an explanatory idea rather than a system capability.

The second decision is the unit of evidence. Research demos often report one success metric, but tactile manipulation improves through failure records. A useful attempt record contains the object or SKU, the selected grasp candidate, the robot hand and sensor configuration, calibration version, task phase, tactile summary, policy action, safety intervention, and final outcome. This record is what connects the sensor chapters to the data chapter, the control chapters to the learning chapters, and the manufacturing chapters to QA.

The third decision is where the chapter sits in the control stack. Some ideas belong in fast reflex loops, some in contact MPC, some in policy inputs, and some only in offline diagnosis. Mixing these time scales creates brittle systems: a VLA cannot react to millisecond slip, and a low-level force controller cannot infer the next process step. The right architecture separates fast contact stabilization, mid-level grasp or rearrangement control, and slow task reasoning.

Finally, the chapter should be evaluated by the failure modes it removes. A method that improves benchmark success but leaves the team unable to distinguish perception failure, contact-acquisition failure, force-closure failure, execution-time slip, or maintenance drift is not yet production-ready. A method with slightly lower headline performance but better logs, safer force limits, and clearer recovery hooks may be the stronger basis for manufacturing Physical AI.

Chapter-Specific Implementation Framework

Turning slip and shear into a working system begins with state definition. The concept should not remain an abstract performance claim; it should become a variable that a controller and a logger can both read. For this chapter, the relevant state may include slip margin, contact patch, normal force, shear direction, object pose, task phase, safety margin, operator override, and product-damage risk. Each variable needs a coordinate frame, a timestamp convention, a calibration version, and an owner in the control stack. Without this discipline, a successful trial is hard to explain and a failed trial is almost impossible to diagnose.

The second step is time-scale separation. A fast loop at hundreds of hertz or 1 kHz should handle motor current, force derivatives, shear spikes, and slip reflexes. A mid-level loop at tens of hertz should update contact pose, grasp phase, and reference finger motion. A slower task loop should reason over object identity, SKU, fixture state, instruction, and the next grasp candidate. slip and shear must be assigned to the right layer. A VLA cannot react to millisecond slip. A low-level force controller cannot infer the next process step. A robust architecture lets these layers communicate through compact state summaries rather than forcing every signal into one monolithic policy.

The third step is a record schema. A useful attempt record should contain attempt id, robot-hand model, sensor layout, calibration version, task phase, object or SKU id, selected grasp, measured contact patch, normal and shear force summary, slip event, policy output, safety intervention, operator note, and final outcome. In a manufacturing cell this record is also a QA trace. A research demo can be persuasive with a video, but a production experiment needs replayable evidence. For that reason, the result table for slip and shear should include failure-type distribution, retry count, product-damage rate, cycle-time variance, and intervention frequency alongside success rate.

The fourth step is a small test protocol. Starting with every object and every hand motion makes failures uninterpretable. A better protocol begins with atomic tasks: contact acquisition, stable hold, controlled release, contact switch, recovery after slip, and force-limited correction. The next stage composes two or three atoms into sequential manipulation. Only after that should the system attempt a Cosmax-style first grasp, in-hand rearrangement, and second grasp sequence. This staged protocol reveals whether slip and shear actually removes a failure mode or merely shifts the failure later in the trajectory.

The fifth step is to treat hardware and maintenance as experimental variables. The same algorithm can behave differently when gel surfaces wear, pads become contaminated, cable tension changes, a sensor is replaced, calibration drifts, backlash grows, or surface humidity changes. The log therefore needs software version, pad age, cleaning state, calibration time, replacement event, and fault code. These fields are not administrative details. They determine whether a performance drop comes from the learned policy, the contact model, the sensor, the hand mechanics, or the production environment.

The sixth step is failure-driven decision making. The team should ask which failure class improves after adding slip and shear: perception before contact, contact acquisition, force-closure insufficiency, execution-time slip, collision, product damage, or operator override. If the answer is unclear, the method is not yet actionable. If the answer is clear, the next investment becomes much easier to choose. A contact-state problem suggests better sensing or calibration. A closure-margin problem suggests hand geometry or force control. A replay mismatch suggests simulation fidelity. A repeated intervention suggests task design, fixture design, or operator workflow.

Validation Protocol: From Demonstration to Repeatable Evidence

The method in this chapter should be validated as a repeatable experiment, not as a single successful demonstration. The first step is to lock the reset condition. Object pose, hand initialization, sensor calibration, pad condition, lighting, fixture state, and software version should be recorded before every trial. If those variables drift silently, the team cannot tell whether tactile feedback improved the behavior or whether the experiment simply became easier.

The second step is planned disturbance. Rotate the object slightly, vary surface friction, delay one fingertip contact, perturb the grasp candidate, or introduce a mild occlusion. A tactile method should degrade gracefully under these disturbances. More importantly, the log should show which signal was used for recovery: normal force, shear direction, slip event, contact patch migration, motor current, or a learned latent state. Without planned disturbance, the system may look robust while only succeeding in the narrow reset condition.

The third step is ablation. Compare no tactile input, normal force only, normal plus shear, slip-event tokens, and the full tactile summary. If performance improves only when the full high-dimensional stream is used, the method may be powerful but expensive. If a compact contact summary gives most of the gain, it may be the better manufacturing design because it is easier to log, debug, and transmit across control layers.

The fourth step is recovery-oriented metrics. A contact-rich system will still fail. The question is whether it notices earlier, recovers faster, retries safely, or leaves a clearer diagnosis. Useful metrics include time from slip onset to correction, force overshoot, contact reacquisition time, number of safe retries, intervention frequency, and product-damage near misses. These metrics often matter more than the final binary success rate.

The final step is deployment rehearsal. A researcher-adjusted experiment and an operator-run procedure are different systems. The operator should replace the sensor or pad, run calibration, start the task, stop after a fault, and export logs using the intended procedure. If performance collapses during this rehearsal, the bottleneck is not the policy alone; it is the integration and maintenance workflow. Passing this rehearsal is what turns a tactile manipulation method into a candidate for a manufacturing cell.

Control Design Pattern: Turning Tactile Signals into Actions

The four chapters in Part III return to the same operational question: when the hand receives tactile evidence, what should the fingers do next? A practical answer is a three-stage pattern. First, do not map the raw tactile signal directly to action. Convert it into contact belief: where the contact is, which direction force is applied, how much margin remains, whether slip is likely, and whether the next contact transition is feasible. Second, split that belief into a safety gate and a reference update. The safety gate prevents excessive force, slip, collision, and product-damage risk. The reference update changes target finger pose, target force, internal force, or release timing. Third, feed these results back to the higher-level policy so it can choose the next mode.

This pattern matters most in manufacturing multi-object tasks. Declaring that the first object is stable does not only mean that grip force is high enough. It means that the remaining contacts can support the object if one finger is released, that palm support is real rather than assumed, that the approach path for the second object is open, and that the slip margin is still acceptable. Tactile sensing updates this judgment continuously. Therefore the contact controller's output should not be a single command such as "grip harder." It should include a discrete mode such as hold, release, shift, roll, regrasp, or abort, plus finger-level references for position, force, or torque.

Experiments should evaluate the quality of these mode transitions. At each transition, check whether force spikes appear, whether the contact patch moves in the expected direction, whether shear remains inside the friction cone, whether object-pose estimates agree with tactile evidence, and whether the controller recovers without operator intervention. These logs reveal whether the problem is controller design, hand morphology, sensor placement, calibration, or the task fixture. Without transition-level evidence, a high success rate can hide a brittle policy that only works because the reset condition is narrow.

The same pattern also clarifies the relationship between model-based and learned control. A contact model can propose which mode transition should be possible. A learned residual can compensate for friction, compliance, and unmodeled geometry. Tactile feedback decides whether the proposed transition is actually happening. If the three disagree, the system should slow down, increase observation, or abort rather than blindly completing the motion. This is the control-level meaning of using touch as a first-class signal.

Operator Handoff and Safe-Stop Criteria

In a manufacturing cell, tactile control must end in an operator-understandable procedure. The system should expose when it continues, when it slows down, and when it stops. If slip margin drops, the controller may increase grip force within the allowed envelope. If the contact patch leaves the expected region, it may attempt a regrasp. If force limits or product-damage risk are exceeded, it should enter abort mode immediately. These conditions should not be hidden inside the policy. The operator interface and QA log should use the same names as the controller.

A useful handoff record contains three fields. The first is phase: acquire, hold, shift, release, regrasp, or abort. The second is stop reason: slip, over-force, lost contact, pose uncertainty, collision risk, hardware fault, or calibration drift. The third is next action: automatic retry, operator confirmation, sensor cleaning, recalibration, fixture reset, or object removal. This makes tactile control a shared operating procedure rather than a black-box behavior. It also gives the engineering team a direct path from field failures back to controller changes, sensor maintenance, or task redesign.

References

1. Lin, T., et al. (2025). PP-Tac: Paper pick-and-place with tactile diffusion policy. arXiv preprint. source [Lin et al., 2025]
2. Qi, H., et al. (2023). AnyRotate: Gravity-invariant in-hand object rotation with sim-to-real touch. CoRL 2023. source [Qi et al., 2023]
3. Sievers, L., et al. (2022). Learning purely tactile in-hand manipulation with a torque-controlled hand. ICRA 2022. source [Sievers et al., 2022]
4. Sharpa. (2026). CraftNet and Sharpa Wave product information. source [Sharpa, 2026]
5. Cosmax Robotics Meeting. (2026b). Model-based approach vs RL-based approach for in-hand manipulation. Internal meeting PDF, 2026-06-05. private source [Cosmax, 2026b]