**5. Experiments**

The complete network diagram is shown in Figure 14. All the PCs of this network communicate via ROS. The two assistive strategies are implemented in the right laptop, which recovers FT sensor information from the two middle PCs and sends robot commands to the left PC.

**Figure 14.** Network diagram of the Exoscarne system. From left to right: control box of the KUKA LWR 4+ robot connected to one PC with FRI/KDL libraries; data acquisition boxes for FT sensors A and B connected to two PCs and an Arduino board for joystick acquisition connected to a laptop.

We performed experiments to address the following questions:


#### *5.1. Comparison of FT Sensors*

As shown in Figure 10, there were two FT sensors on the cutting tool. We wanted to confirm if 2 FT sensors provide an advantage over a single FT sensor, as well as determine which FT sensor is better as a source of input for the control scheme.

A piece of thick foam was used as the material to be cut. This foam reproduces the same type of shearing forces as meat cutting. Two experiments were performed. In the first one the robot was commanded to apply forces gradually from 0 to 50 N in the Y-direction of the world frame, which was parallel to the cutting direction of the knife. In the second experiment, a human cut the foam multiple times in the Y-direction, as shown in Figure 15.

Based on the sensor readings from both the sensors, it was observed that for free motion in space (without any cutting), both the sensors record the same readings. However, for cutting motion, sensor A (refer to Figure 10) is blind to the cutting forces. Sensor B recorded forces when the robot cut the foam autonomously, but the recorded forces were feeble and almost negligible to the forces commanded to the robot. When a human cut the foam using impedance controller the sensor B registered adequate forces.

**Figure 15.** Comparison of sensor A and sensor B.

Hence it was determined that it is reasonable to consider that the forces sensed by sensor B (below the joystick) capture the human applied forces on the knife and thus, the user's intention. During actual meat cutting experiments, both the sensors were alternated as sensor inputs for the controller in numerous trials and the user responded that he preferred the system behaviour when sensor B was the sensor input.

#### *5.2. Impedance Shaping for Cutting*

While cutting meat, the user performs an active meat cutting operation followed by an inactive repositioning of the knife for the next stroke. Furthermore, the user may want to use both of his hands for some other task and as such need the robot to stay still in the last position. The joystick has two buttons (see Figure 10): the first lateral grey button with three possible positions (i.e., a dead-man's switch) and the second upper black button having two states (i.e., a pushbutton). This gives us a total of 6 possible combinations shown in Table 4. The corresponding electrical connections of both buttons are shown in Figure 11.


#### **Table 4.** States of joystick buttons.

The button configurations from Table 4 are interpreted in the impedance shaping algorithm as shown in c. We can see that the last two rows are identical. Originally we tried to use position 2 with an impedance relation (i.e., *K*, *D* ← *Fh*); however, the user preferred to keep the interface simple and make the position 1 and position 2 identical for operation. This shows that developing user-friendly interface is essential for the adoption of pHRI over human-only or robot-only equipment. The constant values of Table 5 are: 0.1 0.1 0.1 0.1 0.1 0.1

*Kmin* =  , *Kmax* =  5000 5000 5000 300 300 300 , *Dmin* =  0.01 0.01 0.01 0.01 0.01 0.01 , *Dmax* =  1.0 1.0 1.0 1.0 1.0 1.0


**Table 5.** Impedance shaping using joystick.

#### *5.3. Tuning the Amplification Factor*

In the force amplification strategy we amplify the forces applied by the user on the joystick, detected by the FT sensor and input to our control scheme (see Figure 1). For the robot to provide assistive forces we had to determine the amplification factor *η* for each degree of freedom as shown in Equation (18):

$$F\_{cmd} = \begin{bmatrix} \ ^c F\_x \\ ^c F\_y \\ ^c F\_z \\ ^c F\_{A\_z} \\ ^c F\_{B\_y} \\ ^c F\_{C\_X} \end{bmatrix} = \begin{bmatrix} \eta\_x \\ \eta\_y \\ \eta\_z \\ \eta\_{A\_z} \\ \eta\_{B\_y} \\ \eta\_{C\_X} \end{bmatrix} \begin{bmatrix} \ ^c\_B F\_x \\ \ ^c\_B F\_y \\ ^c\_B F\_z \\ ^c\_B \tau\_z \\ ^c\_B \tau\_x \\ ^c\_B \tau\_x \end{bmatrix} \tag{18}$$

While a high amplification factor would easen the load on the user, it could also give the user the perception that he is no longer in control of the operation and reduce his comfort with the system (as was realized during the experiments). This is the reason we cannot have the robot simply apply the highest forces possible.

The tuning of the comfortable amplification factors was a continuous process where several iterations of meat cutting were performed by a professional butcher. It was decided collectively that there would be only two amplification factors: one common *η<sup>f</sup>* for forces and one *ητ* for torques (i.e., *η<sup>f</sup>* = *η<sup>x</sup>* = *η<sup>y</sup>* = *η<sup>z</sup>* and *ητ* = *ηAz* = *ηBy* = *ηCx* ). This iterative tuning process finished when the butcher found that the assistance behavior was comfortable, as explained in Figure 16.

The meat cutting operation involves both the application of forces and torques, as such the force amplification factor *η<sup>f</sup>* cannot be determined independently of the torque amplification factor *ητ*. In earlier experiments the user felt that *ητ* = 3 was ideal for him and hence to determine *η<sup>f</sup>* a series of consecutive experiments were done as shown in Table 6 enabling the user to make a subjective comparison.

At the end of the experiment it was concluded that the user preferred *η<sup>f</sup>* ∈ [10, 20] and *ητ* = 3. With *η<sup>f</sup>* = 20 and *ητ* = 4, the user found the system to be too reactive and he felt he was no longer in control. These 6 experiments and the temporal evolution of the cutting forces applied by the user after applying these optimal force amplification factors are shown in the next section.

#### *5.4. Meat Cutting with Force Amplification Strategy*

As a knife mounted on the end-effector of a robot is inherently dangerous, the knife for the meat cutting experiments was always covered with a sheath when not in use to avoid accidental injury. When experiments were being performed, even if the user could stop the robot at any time by releasing the button, a second person always had his/her hand on the emergency robot switch to disable the robot if something goes wrong. The user also wore a protective gear around his arms. In addition, as a precaution, the robot was wrapped with a plastic sheet to prevent minute meat pieces from entering the internal structure of the robot.

**Figure 16.** Iterative procedure for tuning the two amplification factors for forces and torques.

**Table 6.** Determining the force amplification factor *ηF*.


#### **Experiment 1—Cobot assisted pork cutting**

Figures 17 and 18 show the sequence of cuts of Experiment 1 and the corresponding temporal evolution of the XYZ-total forces applied by the user and measured by the B sensor, respectively. The terminology A cut, B cut, etc. in these figures are author defined to refer to the iteration of the cutting and not the cutting methods. Therefore, the images shown in Figure 17 do not represent one single cut in progress, but instead one image of each cut: they can be interpreted as cut 1, cut 2, etc.

(**a**) A cut (**b**) B cut (**c**) C cut (**d**) D cut **Figure 17.** Experiment 1—cobot assisted pork cutting.

**Figure 18.** Forces applied by the user in Experiment 1.

#### **Experiment 2—Cobot assisted pork cutting**

In Experiment 1, it took the butcher (the user) 4 cuts to make 1 slice. Nevertheless, in Experiment 2 (see Figure 19), with the same section but from a different meat, it took him 9 cuts to make 1 slice (see Figure 20 for the corresponding temporal force evolution). This is due to the natural variation in the body composition from one animal meat to another and also how much forces the user wanted to apply for a single cut.

(**a**) A cut (**b**) B cut (**c**) C cut (**d**) D cut (**e**) E cut

(**f**) F cut (**g**) G cut (**h**) H cut (**i**) I cut **Figure 19.** Experiment 2—cobot assisted pork cutting.

**Figure 20.** Forces applied by the user in Experiment 2.

#### **Experiment 3—Cobot assisted pork cutting**

Figure 21 shows the 5 cuts of Experiment 3 while Figure 22 represents the temporal evolution of the forces exerted by the human during those cuts while assisted by the force amplification strategy.

(**a**) A cut (**b**) B cut (**c**) C cut (**d**) D cut (**e**) E cut **Figure 21.** Experiment 3—cobot assisted pork cutting.

**Figure 22.** Forces applied by the user in Experiment 3.

#### **Experiment 4—Manual pork cutting**

Figure 23 shows the 9 cuts of Experiment 4 and Figure 24 represents the corresponding temporal evolution of the forces applied by the human.

(**a**) A cut (**b**) B cut (**c**) C cut (**d**) D cut (**e**) E cut

(**f**) F cut (**g**) G cut (**h**) H cut (**i**) I cut **Figure 23.** Experiment 4—manual pork cutting.

**Figure 24.** Forces applied by the user in Experiment 4.

#### **Experiment 5—Manual pork cutting**

Figure 25 shows the 5 cuts of Experiment 5 and Figure 26 represents the corresponding temporal evolution of the forces applied by the human.

(**a**) A cut (**b**) B cut (**c**) C cut (**d**) D cut (**e**) E cut **Figure 25.** Experiment 5—manual pork cutting.

**Figure 26.** Forces applied by the user in Experiment 5.

#### **Experiment 6—Manual pork cutting**

Finally, Figure 27 shows the 7 cuts of Experiment 6 and Figure 28 represents the corresponding temporal evolution of the forces applied by the human.

(**a**) A cut (**b**) B cut (**c**) C cut (**d**) D cut (**e**) E cut

(**f**) F cut (**g**) G cut **Figure 27.** Experiment 6—manual pork cutting.

**Figure 28.** Forces applied by the user in Experiment 6.

#### **Experiment 7—Foam cutting with intent prediction module**

For the previous meat cutting experiments with force amplification strategy we had a professional butcher as the user. However, for verifying the intent prediction strategy, we used a foam block and multiple users in order to perform the training of the LSTM network (see Figure 29 for the corresponding experimental setup). This foam reproduces the same type of shearing forces as meat cutting.

**Figure 29.** Foam cutting along the global y-direction.

As explained earlier, our intent prediction module uses RNN-LSTM units. For each user, we performed sample trials with foam cutting to collect the training dataset. The LSTM network was trained on this dataset to predict force values, similar to the prediction of force values of the Natural Motion dataset (NM-F) in [23].

For each user we took 90 percent of the sample dataset as the training dataset. The entire architecture consisted of 4 layers- an input layer, an LSTM layer, a fully connected layer and a regression layer. We tested the prediction accuracy with combinations of different hyperparameters such as the number of epochs, sequence length and learning rate. However the results were almost the same i.e., a prediction accuracy of 0.3 (root mean square error).

The number of features was 1 as we had only a single variable—force applied. Similarly as only 1 output was expected, the number of responses was 1. The number of hidden units was taken as 200 and the maximum number of epochs was set to 250. The sequence length for the input layer was 25 time steps (0.2 s). For the output layer, we used Stochastic Gradient Descent algorithm with a learning rate of 0.01. The sigmoid function was used as the activation function for the 3 gates—In, Out and Forget in the LSTM units as it outputs a value between 0 and 1. However for the memory cell, the values should be able to increase or decrease which is not possible with the sigmoid function as the output is always nonnegative, hence we used the hyperbolic tangent function (tanh) as the activation function for the memory cell.

Figure 30 shows the plot of cutting forces applied by a user with and without the intent prediction module (for 30 cm cutting of the foam). When the intent prediction module was turned off, we had *Kmin* and *Dmin* only (i.e. minimum impedance). With the intent prediction module the user applied only 20 percent of the forces as compared to when the module was turned off.

We also compared the force amplification strategy with the intent prediction strategy with 5 users as shown in Figure 31. For each user sample trials were conducted with force amplification strategy for them to decide which amplification factor they are comfortable

with. All the users stated that the intent prediction module made the cutting more intuitive than the force amplification strategy.

**Figure 30.** Cutting forces applied by the user using the intent prediction module for 30 cm cutting of the foam. The blue line is the force applied with *Kmin* and *Dmin* only (i.e. minimum impedance), while the red line is the force applied with *Kmin* and *Dmin* and the intent prediction module.

**Figure 31.** Comparison of different strategies with 5 users.

## **6. Conclusions and Future Work**

In this paper, we demonstrated a proof of concept of two pHRI-based assistive strategies for an industrial meat cutting system. It was determined that sensor B below the joystick gives better reactivity and hence this sensor should be used as the sensor input. From the previous experiments, it is evident that the forces applied by the user are approximately 30% small with the cobot and the force amplification strategy than with the manual meat cutting operation. Blades with lengths 20 cm and 10 cm were tested, and the one with length 10 cm was adjudged to give better cutting performance, because it was stiffer, with less bending and mechanical compliance.

The cartesian impedance controller runs at a frequency of 1000 Hz, as well as the FT sensor. At this frequency the user found it intuitive and useful to operate the tool for the meat cutting task without any issue. However, it is known that the human central nervous system operates at a lower frequency than a robot controller, and if he is coupled to the system via a tool it is possible for the user to 'perceive' a loss of control if the system is too reactive, an observation that capped the upper limit of the amplification in the force amplification strategy.

In the foam cutting experiment, it was shown that the intent prediction strategy was better than the force amplification strategy, especially with regards to intuitiveness. In a pHRI system such as this one, not only should the robot provide assistance as a machine, but also the interface should be intuitive, natural and easy to use.

Our contributions are:


For future work, we would like to compare the force amplification strategy and the intent prediction strategy on meat cutting tasks. Furthermore, in the current experiments we had only one professional butcher and it would be interesting to see what are the experimental results with more professional users. The next step of project Exoscarne would involve the design and development of a specific exoskeleton for meat cutting and transferring the controller that was developed in this work.

**Author Contributions:** Conceptualization: H.M., J.A.C.R., Y.M.; methodology: H.M., J.A.C.R., L.L., Y.M., M.A.; software, H.M., L.L.; validation and analysis: H.M., M.A.; writing—original draft preparation: H.M.; writing—review and editing: J.A.C.R., L.L., Y.M., M.A.; supervision: J.A.C.R., Y.M.; funding acquisition: J.A.C.R., Y.M., M.A. All authors have read and agreed to the published version of the manuscript.

**Funding:** This research received funding from the French government research program Investissements d'Avenir through the UMTs ACTIA Mécarnéo-AgRobErgo and the project Exoscarne (Call P3A-ICF2A-2I2A, FranceAgriMer) and from the European Union's Horizon 2020 research and innovation programme under grant agreement nº 869855 (SoftManBot project).

**Informed Consent Statement:** Informed consent was obtained from all subjects involved in the study.

**Conflicts of Interest:** The authors declare no conflict of interest.

#### **Abbreviations**

The following abbreviations are used in this manuscript:

