In this paper, we address the problem of terrain classification using a technically blind hexapod walking robot. The proposed approach is built on top of the existing method based on analysis of the feedback from the robot's actuators and the desired trajectory. The formed method uses features for the Support Vector Machine classification method that assumes a regular time-invariant gait to control the robot. However, such a gait does not allow the robot to traverse rough terrains, and therefore, it is necessary to consider adaptive motion gait to deal with small obstacles, which is, unfortunately, not a regular gait with some fixed predefined period. Therefore, we propose to alter the features extraction process to utilize the terrain classification method also for an adaptive motion gait, which enables the robot to traverse rough terrains. The proposed method has been experimentally verified on several terrains that are not traversable by a default regular gait. The achieved results not only confirmed the high accuracy of the terrain classification as the existing approach, but also expanded the area of operation of a hexapod walking robot into more challenging terrains.
Crawling robots can operate in a much greater scope in
terms of terrain diversity than classical wheeled robots.
The control complexity is, however, much greater due to
the high number of degrees of freedom (DOF). One way
to handle a high DOF is to generate a walking pattern—a
gait [
In order to increase the robot’s perception of the
environment—for example to classify the terrain the robot
is traversing—one can employ the robot with a variety
of sensors. There can be found two complementary
approaches based on exteroceptive and interoceptive sensors.
In the case of exteroceptive sensing, we can utilize
camera [
However, if the robot is technically blind and
dependent solely on interoceptive sensing, we can use force,
torque [
The existing method [
The paper is organized as follows. A brief overview
of the adaptive motion gaits for rough terrains and
terrain classification methods is provided in the next section.
A description of the considered robotic platform and
definition of the problem is presented in Section 3. The
utilized adaptive motion gait is briefly described in Section 4.
The proposed feature extraction method is presented in
Section 5 and experimental results in Section 6. The
concluding remarks are in Section 7.
approaches can be found in literature. A complex control
architecture of quadruped walking robot to traverse
challenging terrains has been presented in [
Another existing direction of the adaptive motion gaits
are based on approaches that do not utilize a terrain map.
They are based on a tactile information from force
sensors [
The problem of terrain classification is widely
investigated also regarding on-board processing. A camera can
be used to estimate the terrain class based on extracted
features [
Focusing on a structural point of view, an off-line scan
of the terrain from a precise external laser-scanning system
was used in [
Beside exteroceptive sensing, tactile sensors are used to
classify the terrain based on the direct measurements of
the robot interaction with the terrain. In [
A slightly different approach that utilizes only
interoceptive sensors built within the actuators was presented
in [
In this paper, we proposed a combination of the terrain
classification method [
The main problem being addressed in this paper is to
extend the existing terrain classification approach [
The used hexapod platform has six legs each with three joints formed from the Dynamixel actuators. The schema of the leg and the description of its parts is depicted in Fig. 2. All joints (θC, θF , and θT ) are controlled with a position controller that provides every 33 ms the following information: • Desired position θ des; • Current position θ cur; • Error in position e = |θ des − θ cur|.
Using the adaptive motion gait [
r u em
F
θF
a
i
b
i
T
θT
We consider the robot is operating in an environment that
satisfies the robot’s structural limits and there is not a large
obstacle that the robot cannot traverse. Hence, we are not
addressing obstacle avoidance and other high-level
navigation problem in this paper. Thus we are strictly focused
on the problem of terrain classification and its practical
validation in real experiments.
3.2
The method of the terrain classification [
In order to obtain a more dense data and to get a uniform sample rate for the FFT used in the feature extraction, the signal is interpolated using a cubic Hermite spline interpolation method that creates a continuous function with a continuous first derivative. The interpolated function is then resampled at the frequency of 100 Hz. After that, a feature vector for the classification is created from the sampled data and computed characteristics of the signal.
Having the default regular gait, the data is windowed using a uniform window that contains the last three full gait cycles; so, each terrain-class prediction is based on the past three gait cycles worth of data. Given the motivation that different terrain surfaces induce a specific behavior in different sections of the gait cycle, the data are divided into 16 equally wide segments within a gait cycle to form a gait-phase domain. Respective segments from the last three gait cycles are joined together and basic statistics of all data samples that fall within are computed yielding in 5 values (features) for each segment (i.e., minimum, maximum, mean, median, and standard deviation). Repeated for each servo, we obtain a total of 480 gait-phase features, i.e., 2 (legs) × 3 (servos per leg) × 5 (features) × 16 (segments).
Additional 180 features are calculated in the frequency domain. A Hamming window and discrete Fourier transform are applied on the same resampled position error signal to obtain a frequency spectrum of 25 bins (0–12 Hz). All amplitude values of frequency bins are used alone, giving another 25 features (for each servo), supplemented by 4 features obtained from the shape of the spectrum (i.e., centroid, standard deviation, skewness, and kurtosis) and finalized with the energy of the spectrum. The overall 660-dimensional feature vector consists of: • Statistics of each segment for each servo (5 × 16 × 6 = 480); • Bins of the frequency spectrum (25 × 6 = 150); • Shape of the frequency spectrum (4 × 6 = 24); • Energy of the frequency spectrum (6).
Such 660-dimensional feature vectors for particular
type of the terrain and several trials of traversing the
terrain are used to train a multi-class linear Support Vector
Machine (SVM) classifier and authors of [
In our approach presented in this paper, we follow the same idea of the terrain classifier based on the SVM, but we propose a new feature extraction process to address the absence of regularity in the adaptive motion gait for crawling rough terrains. 4
The adaptive gait is originally based on a regular tripod gait in terms of predefined trajectories for each particular leg. However, the trajectories can be changed and the gaitcycle is divided into separate phases of the leg and body motion.
g n i l e v e L y d o B
STABLE STATE
(R, ~t ) from leg positions
The gait diagram is shown in Fig. 3, where it can be seen that legs in the transfer phase move through predefined checkpoints (up and forward) and begin approaching another predefined checkpoint, which is situated far below the current ground level (but still reachable). The ground sensing is done via observing the position error e of the joint θF during lowering the leg with respect to a certain threshold value. Although all legs in the transfer phase are moving simultaneously, each ground contact stops only the particular corresponding leg.
After the legs found their new footholds (the rest legs stay motionless), a new body posture is found given the feet positions in order to adapt to the terrain the robot is traversing. The body motion itself is provided by moving all legs according to a transformation of the feet positions.
In summary, the leg motion phase consists of 3 steps
(up, forward, and down) and is followed by a body leveling
step. Given the tripod gait in which the legs are grouped
into two triplets that are alternating, we repeat the same
steps for the other triplet to obtain a total of 8 discrete steps
per one full gait cycle. Notice, that as a consequence of the
adaptive-gait model, a leg is moving only in the transfer
phase (3 steps) and in both body leveling steps (4th and
8th steps), where all legs are needed to move the body.
A more detail description can be found in [
The proposed feature extraction process is based on the
terrain classification originally developed for a regular
gait [
A leg trajectory during the phases of the gait is depicted
in Fig. 4. The regular gait is periodic and the robot is able
to traverse a flat terrain at the constant speed. Although
the robot can pass very small obstacles at the cost of a
high servo load, the robot is incapable to traverse a rough
terrain using this regular default gait [
On the other hand, the adaptive motion gait utilizes a tactile information to detect the ground-contact point and thus it is able to decrease the servo load and adjust the robot to the terrain. However, ground-contact points along the vertical line (during moving the leg down) are not known. Hence the time the leg spends in the groundapproaching phase is also not known. Moreover, the trajectory of the particular foot in the support phase is also influenced by the contacts of the other legs with the grounds, and therefore, the trajectory is not regular during crawling rough terrain and it may vary significantly. These variances have to be considered in the analysis of the servo position signal in the feature extraction process to avoid possible misinterpretation of the data.
Transfer
phase
(a) Default gait p U
D o w n
Due to the variances of the gait phases, which depends
on the roughness of the terrain the robot is traversing, we
cannot rely on a uniform partitioning of the gait phases
into 16 segments for the feature extraction as in [
Authors of [
Since the proposed method extends an existing approach by adding more rough terrains where the robot can operate, we focused the experimental evaluation of the proposed method solely on those challenging terrains. Nevertheless, we also used datasets from simple outdoor terrains for completeness.
The proposed multi-class SVM classifier (with linear kernel) was trained for feature vectors collected from 7 different classes: • Wooden stairs • Wooden blocks of different height • Office floor with small obstacles • Office floor • Asphalt • Grass • Dirt (a) Small obstacles (b) Wooden blocks (c) Wooden stairs The outdoor terrains (grass, dirt and asphalt) are very flat and easily traversable by a default regular gait. However, the rough terrains shown in Fig. 5 are traversable only by the used adaptive gait. Default gait is able to traverse only small obstacles (cf. 5a) and this simple terrain type is used to fill a gap between the flat terrains (outdoor and office floor) and the rough terrains (blocks and stairs).
Dirt Asphalt Grass Office Obstacles Blocks Stairs 62 1 0 0 0 0 0
Each terrain class was trained from several trials with 3–7 minutes worth of data; the exact number of feature vectors extracted from the data can be read from columns of Table 1.
The evaluation strategy is based on the verification of the distinguishability of the terrain using the features. Then, we evaluate online detection of the terrain in a separate scenario, where particular types of the terrains are altered and the robot is requested to traverse them and continuously detect the terrain. These two evaluation scenarios are described in the following sections. 6.1
Two-fold cross-validation with all datasets involved has been used to validate whether the classifier is able to distinguish between the considered 7 terrain classes. As can be seen from the confusion matrix in Table 1, the overall accuracy of 99.4% is very high even for only 2-fold crossvalidation (with more folds, we can easily get 100%).
However, notice this test is based on using always data
from the same single experiment in both training and
testing partition, and therefore, the data are more likely
referring to themselves than to a generalized model of
particular terrain class. In [
A more realistic practical scenario is based on evaluation of the classification for traversing rough terrains in a single run, where undefined terrains at the overlap of the particular terrain types are provided. The scenario setup is shown in Fig. 6 and it consists of a sequence of rough terrains used for the learning. The robot starts from a defined position and crosses progressively few small obstacles, a pool of wooden blocks, and wooden stairs. This scenario was repeated five times and the extracted feature vectors were evaluated against the model previously learned from a single-pass of the individual terrains.
The predicted terrain labels from each of five runs are shown in Fig. 7. The class prediction is made once per each gait cycle and is computed from the last three gait cycles worth of data. Therefore (with respect to the robot’s length) there are long transition areas of the overlapping terrains.
The transition between the office floor and the pool of wooden blocks is mostly characterized as the stairs, which corresponds with the entry side of the pool with increasing height of the blocks.
The other transition between the blocks and the stairs is undefinable and can be predicted as either terrain class, or a similar class (obstacles) based on the actual footholds in the area during the experiment. We can also see that there is some confusion between the dirt and the office floor terrain with obstacles which are both relatively flat and slippery for the robot.
Despite not analyzed, if another terrain class of stairs being traversed down was trained, it is highly probable that a transition from the blocks to the office floor would have been classified as this terrain (for the same reason as the opposite transition mentioned above).
The main aspect of the challenging terrain traversing, which cannot be seen on the simple flat terrains, is the
Gait cycle:
Run #1 Run #2 Run #3 Run #4 Run #5 Legend: dirt obstacles blocks stairs grass occurrence of a foot slippage on the edge of an obstacle (stair) that yields in a sudden fall to a lower level and impacts all legs. More slippages in a short time can lead in a confusion in the prediction, as can be seen in Fig. 7 where the transition between the blocks and the stairs was once predicted as a grass terrain.
The unequal length of all runs is purely dependent on the event when the robot steps over the side edge of the stairs and thus stops the experiment. This happens due to the fact that the robot cannot steer and is strictly going straight ahead.
Notice, it is not possible to show the ground truth for the predictions in Fig. 7 because the robot can spend different number of gait cycles to get to the same point in the scenario in particular runs. Therefore, the only measure we can get is to compare the results from Fig. 7 to the overview of the testing scenario shown in Fig. 6. 7
We proposed an alternative method to extract features from servo drives to classify terrains for a technically blind robot traversing rough terrains. Although the proposed method simplifies the original feature extraction process, the results indicate it is sufficient to distinguish evaluated terrain classes. Moreover, the results also indicate we can employ the learned classifier in the on-line terrain classification in scenarios with rough terrains.
The classifier is based on the features of the robot motion and interaction with the terrain. However, the features of the terrain itself (e.g., slopiness, slipperiness, convexity) are not analyzed directly—they may be hidden inside the SVM layer and could be addressed in the future work.
The presented work has been supported by the Czech Science Foundation (GACˇ R) under research project No. 15-09600Y.