Documente Academic
Documente Profesional
Documente Cultură
Abstract—The vehicle-following concept has been widely used vehicle both longitudinally and laterally. This intuitive behavior
in several intelligent-vehicle applications. Adaptive cruise control comes to its limitations when other traffic participants interfere
systems, platooning systems, and systems for stop-and-go traffic with the leader-vehicle’s path. Dynamic path modification be-
employ this concept: The ego vehicle follows a leader vehicle
at a certain distance. The vehicle-following concept comes to its comes necessary. These dynamic driving situations motivated
limitations when obstacles interfere with the path between the ego the work of this paper.
vehicle and the leader vehicle. We call such situations dynamic How is this paper organized? Section II gives an overview
driving situations. This paper introduces a planning and deci- of related work both in the fields of intelligent vehicles and
sion component to generalize vehicle following to situations with robotics. In Section III, the elastic-band framework is intro-
nonautomated interfering vehicles in mixed traffic. As a demon-
strator, we employ a car that is able to navigate autonomously duced. Section IV describes the necessary adaptations to the
through regular traffic that is longitudinally and laterally guided elastic-band framework in order to tune the avoidance behavior
by actuators controlled by a computer. This paper focuses on toward that of human beings. In Section V, the extension of
and limits itself to lateral control for collision avoidance. Pre- the elastic-band approach to nonholonomic vehicles is briefly
viously, this autonomous-driving capability was purely based on discussed. The impact of the elastic-band framework on the
the vehicle-following concept using vision. The path of the leader
vehicle was tracked. To extend this capability to dynamic driving planning and decision module is described in Section VI.
situations, a dynamic path-planning component is introduced. Results are detailed in Section VII. Conclusions and future
Several driving situations are identified that necessitate responses work comprise the final section.
to more than the leader vehicle. We borrow an idea from robotics
to solve the problem. Treat the path of the leader vehicle as an
elastic band that is subjected to repelling forces of obstacles in the II. R ELATED W ORK
surroundings. This elastic-band framework offers the necessary
features to cover dynamic driving situations. Simulation results A. Potential Field Approaches
show the power of this approach. Real-world results obtained with
our demonstrator validate the simulation results. The most prominent idea for collision avoidance in robotics
applications is artificial potential fields (e.g., [5] and [6]). The
Index Terms—Computer vision, intelligent vehicle, robotics,
stereo vision. obstacles are modeled as potentials and the gradient of the
superimposed potential field yields the direction command for
the mobile robot. Potential fields are an elegant way to model
I. I NTRODUCTION obstacles and can be analyzed globally. A formal verification of
the obstacle-avoidance behavior is analytically feasible.
C OLLISION avoidance has been the subject of extensive
research both in the fields of robotics and intelligent vehi-
cles. Since research on autonomous robots has been conducted
Generalized potential fields depend—not only—on distance
to obstacles but can also depend, e.g., on obstacle velocity.
for more than two decades, the lessons learned in that field also Therefore, these fields can determine irrelevant obstacles mov-
benefit the intelligent-vehicle research. A tremendous benefit ing away from the ego vehicle. This method was first applied
is assessed for reducing collisions with automated systems in using velocity-dependent potentials in [5].
regular traffic [1]. The detection capabilities of vision-based A popular approach to avoid local minima, i.e., trapping
intelligent vehicles are mature enough to perform such a task situations, in potential field applications is the use of harmonic
(see, e.g., [2]). potentials (see, e.g., [7] and [8]).
For lateral vehicle guidance on highways, vision-based lane
following is a promising and well-tested strategy (see, e.g., [3]). B. Approaches Using Physical Models
Recent work on lane recognition in urban areas is described in
[4]. However, lane following relies on lane markings and tends Other physical models besides potential fields are also popu-
to fail in cluttered scenes and in urban areas. Hence, a popular lar for collision avoidance.
approach for automated vehicle guidance is to follow a leader An alternative approach to the potential field method is
presented in [9], where analogies of this problem to hydro-
mechanics problems are shown. Fluid dynamics equations are
used. The fluid starts at the starting point toward the goal point,
and obstacles obstruct the flow. From the resulting flow field,
Manuscript received March 1, 2004; revised October 13, 2005, June 7, 2006,
October 7, 2006 and October 11, 2006. The Associate Editor for this paper was the planned path can be computed.
S. Darbha. In [10], an approach to behavioral control of robots is de-
The authors are with the DaimlerChrysler Research and Technology AG, scribed that uses the model of dynamical systems. Obstacles
71059 Sindelfingen, Germany (e-mail: stefan.gehrig@dcx.com; fridtjof.stein@
dcx.com). generate a stimulus that repels the autonomous robot. The
Digital Object Identifier 10.1109/TITS.2006.888594 path for navigation and obstacle avoidance is generated solving
1524-9050/$25.00 © 2007 IEEE
234 IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, VOL. 8, NO. 2, JUNE 2007
Consequently, the internal force fint is computed via points is sufficiently small, i.e., until the force equilibrium is
reached.
qi+1 − qi qi−1 − qi Pathological situations such as two obstacles located closely
fint (qi ) = −∇q Vint = kc + . (2)
qi+1 − qi qi−1 − qi to the left and right of the initial path might yield an oscillatory
behavior. We reduce the moving factor α after a certain number
This normalized force ensures the same avoidance behavior of iterations to reduce these oscillations.
independent of the band length. Brent introduces an optimization algorithm that minimizes a
function of one variable without computing derivatives and per-
C. External Force forms very few evaluations of that function [26]. This procedure
is used in the original approach to find the force equilibrium,
The external force is due to obstacles that are modeled as
but it is less efficient for situations where only very few path
potentials in the scene. Any potential shape that repels the
modifications occur.
elastic band from obstacles is conceivable. We decided to use
In the original elastic-band approach, the moving procedure
Quinlan’s position-dependent potential [24] superimposed by
is supplemented with a procedure of adding and removing par-
Krogh’s velocity-dependent potential [5]. The gradient of this
ticles in order to maintain a collision-free path at all times (see
potential fext yields the external force. Details on the external
Section IV). So-called bubbles model the available free space
force follow in Section IV-E.
around a configuration. Adding particles becomes necessary
when two adjacent bubbles no longer overlap. Bubbles are
D. Constraint Force circles with a radius of the minimum distance to the closest
The elastic band potentially reduces its internal energy by obstacle for our 2-D case.
moving particles along the elastic band. This is an undesired To speed up convergence of the elastic-band algorithm, the
property since the band might thin out at some parts. To final configuration from the last time step can be used as the
constrain the motion along the elastic band, a constraint force initial configuration for the next time step. Path transformations
fconstr is introduced with the direction t have to be performed to account for the interframe egomotion.
The required modifications of the original approach for the
t = qi+1 − qi + qi − qi−1 (3)
vehicle-following scenario are detailed in the next section.
qi+1 − qi qi − qi−1
tangential to the elastic band. The force is computed by projec- IV. A DAPTATIONS FOR V EHICLE F OLLOWING
tion of the external force along the elastic band A. Basic Idea
2) driving too close to parking cars due to the smaller size the x−z-plane and cannot be adequately described by rectan-
of the leader vehicle; gles. The convex hull is computed with a recursive algorithm
3) driving around a car that comes to a stop slightly inside described in [31] that works in O(n · log(n)), where n is the
the road intersection; and number of points.
4) driving around a pedestrian that moved one step into The relative velocities of the objects with respect to the
the road. ego vehicle are computed based on the center of the obstacles
Many more scenarios can be identified. In addition, further ex- bounding boxes using an extended Kalman filter, assuming
tensions of the autonomous-driving capability of such a vehicle rigid objects. One of the extracted objects is the leader vehicle
definitely need this dynamic path-planning component. supplying the initial path. The other detected objects constitute
The following sections cover the sensor system, details on obstacles.
the distance computation to obstacles in the scene, algorithmic
modifications to the elastic-band approach, potential shapes for C. Efficient Distance Computation
obstacles and lanes, and the actual integration of the approach
The distance of the ego-vehicle path to the obstacles is the
in our demonstrator.
most important quantity for the determination of the external
force on the elastic band. Since the distance is computed
B. Sensor System thousands of times in one cycle, it is of uttermost importance
to compute it fast.
Our range sensor delivers a list of objects in the scene. We
If the ego-vehicle path is not influenced by the potential
use a calibrated stereo camera system to obtain 3-D information
generated by the bounding box of the obstacle, no refined
of the car’s surroundings. However, the elastic-band algorithms
distance computation is necessary, and the distance between the
in this paper are applicable to any sensor delivering range data
bounding boxes is sufficient. The algorithm described below is
with a “suitable” angular resolution.
only necessary for obstacles being close to the ego vehicle. This
The calibrated stereo camera system delivers 3-D measure-
coarse-to-fine strategy saves a significant amount of computa-
ments of significant points resulting in a sparse 3-D-point cloud
tion time.
(less than 500 3-D measurements). The significant points of the
Distance computation between two convex polyhedra is de-
left image are matched in the right image by correspondence
scribed, e.g., in [32]. This algorithm is comparatively fast in
analysis along the epipolar line similar to [28]. With a baseline
general but solves the distance computation in more than two
of about 30 cm, we are able to detect obstacles robustly up to
dimensions. Lin introduces a good incremental algorithm for
40 m with decreasing accuracy for faraway objects. The lateral
the distance computation, but the initial distance computation
position precision of the leader depends on many circumstances
is slow [33]. Faster implementations are available in two di-
(visibility conditions, shape of the leader vehicle, . . .). Empir-
mensions. A very simple method in robotics to account for
ically, we compared the position against hand-labeled leader-
the dimensions of the ego vehicle and the obstacles in distance
vehicle positions and determined a standard deviation of about
computation is obstacle growing. There, the obstacles grow by
20 cm. To further increase lateral position accuracy, one could
the size of the ego vehicle. However, this works only accurately
also apply classification schemes such as described in [29]. It
for circular ego vehicles.
is also possible to employ modern dense stereo techniques to
In our approach, the distance computation between a rectan-
obtain dense 3-D clouds [30].
gle (our ego vehicle) and a convex hull (obstacle) is reduced
To extract objects from 3-D measurements, we apply a spatial
to a distance computation between two line segments. The ego
clustering method to all 3-D points, except the ones on or below
vehicle’s orientation is parallel to the tangent on the elastic
the ground. Here, we assume a constant orientation between the
band. When the ego vehicle and the obstacle do not intersect,
camera system and the flat road.
the distance is computed from all points of the ego vehicle to
One difficulty in combining range data from different frames
all obstacle points. The points with the minimum distance are
is the matching between consecutive frames. How can we
taken, and the distance of the two adjacent line segments on
match data from one frame to the next? On the symbolic
both sides is computed subsequently. Thus, a total of four line-
object level, this is straightforward. We match objects from
segment-to-line-segment distance computations are necessary.
different frames by requiring them to be close together in space.
The distance between the obtained obstacle line seg-
This procedure works well for small scene changes between
ments and the ego-vehicle line segments is computed using
consecutive frames.
Lumelsky’s algorithm [34]. This algorithm is about five times
We assume a flat environment and use only the x and z
faster than the straightforward approach.
coordinates of the objects for collision avoidance.
One object corresponds to one-clustered 3-D-point cloud
D. Modifications to the Original Elastic-Band Approach
projected to the x−z-plane represented by its convex hull for
collision avoidance purposes. A convex hull of a set of points Taking the elastic-band framework over to the intelligent-
is defined as the smallest convex polygon containing the points. vehicle realm, the equations introduced in Section III stay the
In our algorithm, the convex hull represents the outline of an same. The distance computation of the previous section is used
obstacle, which is better suited than the rectangular description to compute the external force. Since our vehicle-following sys-
such as a bounding box. Moreover, objects such as a crowd of tem operates at small velocities, no vehicle dynamics are taken
people standing close to each other exhibit arbitrary shapes in into account. In addition, including vehicle dynamics would
GEHRIG AND STEIN: COLLISION AVOIDANCE FOR VEHICLE-FOLLOWING SYSTEMS 237
also suggest a coupling of longitudinal and lateral control, tainties in the 3-D measurement of objects and uncertain-
which we wanted to avoid to make the algorithm applicable and ties in the vehicle control require additional slack around
independent of the chosen longitudinal control strategy. the planned path, this is not considered a serious problem.
The vehicle-following application of the elastic-band frame- In addition, the nonholonomic constraint also applies to
work differs from the original idea in the following ways. the leader vehicle and is reflected in the leader-vehicle
1) The initial path cannot be guaranteed to be collision path. However, extending this algorithm to scenarios such
free. Since the initial path is created by the path of the as parallel parking, the nonholonomic constraint has to
leader vehicle, changes in the scene might have occurred be considered. Work on elastic bands for nonholonomic
since the leader vehicle has passed. It is possible that vehicles has been presented in [13]. Section V also dis-
another traffic participant has approached that path in cusses this problem.
the meantime. In addition, the leader vehicle might be 5) In regular traffic situations, lane markings are also used
smaller in width than the autonomous vehicle and might for vehicle guidance. The lane markings are detected
have chosen a path very close to an obstacle. and are also modeled as virtual obstacles with repelling
2) The equilibrium position of the configuration particles is forces pointing away from the lane boundaries toward
the leader-vehicle path. We want the autonomous vehicle the lane center. Lanes are modeled as polygons so the
to follow exactly this path in the absence of obstacles. same distance computation algorithm as for obstacles is
Hence, the internal forces of the initial configuration used. More details on the potential shape are presented in
receive an offset yielding zero in the absence of obsta- Section IV-F.
cles. The internal force used for our application is thus 6) When a classification for the obstacle into pedestrian, car,
computed as truck, bicyclist, or other traffic participant is available,
the repulsion factor for obstacles can be varied according
qi+1 − qi qi−1 − qi to the classification result. This way, an additional safety
fint (qi ) = kc +
qi+1 − qi qi−1 − qi envelope can be applied to pedestrians.
qinit,i+1 − qinit,i qinit,i−1 − qinit,i 7) The external force of the elastic band must be shaped to
− − (7) comply with natural driving behavior. Drivers keep more
qinit,i+1 − qinit,i qinit,i−1 − qinit,i
distance from obstacles at high speed than at low speed
where qinit,i is the initial configuration of the ith particle. (e.g., parking situations). Therefore, a velocity-dependent
This also results in an offset term for the total energy of potential shape must be used. The human-like avoidance
the band. This behavior was chosen to maintain the intu- behavior is obtained by empirical parameter tuning of the
itive vehicle-following behavior. Hence, the best strategy parameters appearing in (1)–(13). Details of the external
is to follow the leader-vehicle path unless obstructions potential follow in the next section.
occur. In the original approach, the elastic band was
assumed to have zero length and would always collapse E. Potential Shape for the Obstacles
to a straight line in the absence of obstacles.
3) The concept of bubbles of free space disappears automat- We have experimented with a lot of potential shapes and
ically by allowing initial trajectories that are not collision came to the conclusion that potentials with limited reach best
free. By giving up on the bubble concept, we need an model human driving behavior. Usually, events and objects
additional algorithm to reassure a collision-free path after further away than a certain distance from our planned path do
the equilibrium position has been found. This is done by not have an impact on our actually driven path.
geometrically checking for overlaps along the final con- The original approach for elastic bands is designed for
figuration of the elastic band. Since we model our leader- mobile robots that rarely exceed 2 m/s. Therefore, a position-
vehicle path as a polygon and our obstacles as convex dependent potential is sufficient. We modified this approach in a
hulls, a simple line segment intersection algorithm serves way that the effective reach of Quinlan’s potential deff becomes
the purpose of the overlap check. In our application, we a function of velocity
keep the number of particles constant and equally spaced 2
Vext1,j (q) = 2 kr (deff − dj (q)) , if dj (q ) < deff (8)
1
(typically 1–5 particles/m, the results are presented with
2 particles/m). The procedure of adding and removing 0, otherwise
particles becomes superfluous as well. More generally, deff = d0 + dinc · vego (9)
a collision-free path can never be guaranteed in the
presence of moving obstacles. A drastic example would where Vext1,j denotes Quinlan’s potential of obstacle j at
be a faster car than the one that intentionally wants to position q. For the presented results, we pick deff = 0.3 m and
provoke a collision. Provided sufficient driver skills in the dinc = 0.02 s. dj (q) denotes the distance between obstacle j
“hunter” car, a collision is unavoidable. and particle q of the elastic band; kr is the repulsion gain.
4) A regular car is often treated as a nonholonomic ve- dinc increases the effective reach of the potential for increasing
hicle. The original algorithm applies only to holonomic velocities.
robots. This limitation has not been explicitly taken into In addition, we superimpose a velocity-dependent potential
account. Hence, the paths created by the elastic band introduced by Krogh [5]. Here, we take the velocities of the
could be infeasible for nonholonomic cars. Since uncer- obstacles into account. The magnitude of the potential depends
238 IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, VOL. 8, NO. 2, JUNE 2007
2dj (q )
Tj =
vrel,j
vrel,j Fig. 2. Visualization of the chosen obstacle potential shape. For the situa-
τj = . (12)
a tion depicted in the upper part, the resulting potential can be viewed in the
lower part.
Note that dj,min is only available for obstacle-avoidance
algorithms that plan the whole path. Algorithms only yielding
where dj (q) is the direction vector from obstacle j to particle
current heading and accelerations do not deliver the information
q. The total external energy is computed from
to compute that quantity.
The idea behind Krogh’s velocity-dependent potential is the
Vext = Σj Σi (Vext1,j (qi ) + Vext2,j (qi )) . (14)
following: The minimum avoidance time represents a braking
maneuver with maximum deceleration a. The maximum avoid-
The total energy is easily computed by Etot = Vint + Vext with
ance time uses the full distance to the obstacle and brakes
the constraint force producing no energy.
with a constant deceleration. The reserve avoidance time Tres
When an obstacle is unavoidable for or inside a particle of
is Tres = Tj − τj . The inverse of that reserve time to respond
the elastic band, a maximum force is exerted toward a direction,
to an obstacle represents the potential computed in (10). Note
where obstacle clearance is obtained on the shortest way. De-
that the velocity-dependent potential described here inherits its
tails on how to find this direction are presented in [36]. Roughly,
name from the fact that the potential magnitude and shape de-
this direction is obtained in a simple minimization step, where
pend on the relative velocity between ego vehicle and obstacle.
the obstacle convex hull is approximated by a rectangle.
However, within one time step, this velocity is constant. We
Several restrictions regarding building the gradient of the
use 5 m/s2 as maximum deceleration, which reflects somewhat
potential field apply, e.g., the potential might not even be
suboptimal road conditions.
differentiable at some positions [24]. This might cause the
Fig. 2 shows an example of the chosen potential. In that
algorithm to compute a wrong force in one iteration, but be-
scenario, the obstacle on the right is stationary, whereas the left
cause of a movement of most particles in the elastic band, the
obstacle moves at half the speed of the ego vehicle, which is
situation is resolved in the next iteration. Pathological cases
10 m/s (upper part). The superposition of Quinlan’s position-
might occur where the minimum energy configuration is not
dependent potential and Krogh’s velocity-dependent potential
achieved (local minima, symmetrical situations). In these rare
is depicted in the lower part of Fig. 2.
situations, the final geometrical clearance check assesses the
The total external force per particle is thus
risk of a collision and a potentially unnecessary “switch off”
of the autonomous system is performed. It is not desirable to
dj (q )
fext,j (q ) = kr (deff − dj (q )) · find arbitrary collision-free paths since we want to stick close
dj (q )
to the vehicle-following principle. This is the “advantage” of
Vext2,j (q, vrel,j )2 dj (q ) designing an autonomous system with a human fallback option
+2· · (13)
vrel,j dj (q ) in reserve.
GEHRIG AND STEIN: COLLISION AVOIDANCE FOR VEHICLE-FOLLOWING SYSTEMS 239
even outside the lane, a force toward the lane center is exerted.
The maximum lane force is smaller than the maximum obstacle
force to account for the effect that crossing a lane line is less
dangerous than hitting a real obstacle.
Taking both lane and obstacle information into account
constitutes a fusion of lane-following and vehicle-following
behavior resulting in a humanlike driving behavior.
VI. P LANNING AND D ECISION FOR E LASTIC B ANDS Fig. 4. Simulation result of the elastic-band algorithm (bird view) utilizing
both lanes and obstacles.
In the standard vehicle-following approach, a planning and
decision module selects the leader vehicle and sends the leader-
vehicle position to the controller. A leader vehicle is initially
selected by projecting the planned corridor forward using the
current steering angle, and the first vehicle to intersect with this
corridor is the leader vehicle. The driver has to confirm this
leader-vehicle selection manually.
The elastic-band framework can be integrated easily using
a path-based approach for vehicle following [37]. A reference
frame at rest is created by motion-integration of the own vehicle
motion. The leader-vehicle position is transformed into that
coordinate system for every time step, which yields the leader-
vehicle path. Only the leader-vehicle path has to be exchanged
with the elastic-band path. Due to measurement noise of the
leader-vehicle position, the final elastic-band path is smoothed
using a low-pass filter for the curvature.
The longitudinal control is implemented in such a way that Fig. 5. Simulation result of the elastic-band algorithm using lanes only (bird
we follow the leader vehicle at a safe distance (see, e.g., [40] view).
for such a controller). The same functionality can also be
implemented using fuzzy logic [41]. The elastic-band algorithm VII. R ESULTS
only affects the lateral control. For the rather small avoidance
A. Simulation Results
maneuvers we want to cover within our vehicle-following sys-
tem, this is considered sufficient. For a completely autonomous 1) Simulation Results Without Lateral Control: The initial
system, lateral and longitudinal control must obviously be verification of the implemented algorithms was performed in
coupled. an offline environment, where only a snapshot of a scene was
The corridor to be searched for the leader vehicle becomes analyzed. Parameter tuning was performed in this environment.
the corridor around the elastic-band path. Hence, when small In Fig. 4, a situation is shown, where the leader vehicle is
intersections with an obstacle occur, the elastic-band algorithm slightly driving out of lane and other cars drive to the left and
bends the path in such a way that no intersection with the right. Hence, a slight path modification to the right occurs due
obstacle occurs. As a safety measure, the bent of the elastic- to the obstacles as well as slightly due to the lane markings
band path is monitored, and when deviations beyond a certain with the elastic-band algorithm. Obstacles are modeled as
threshold occur, the control is returned to the driver. Although rectangles for simplicity. The equilibrium state is found within
the elastic band is still feasible in such a case, the behavior 18 iterations.
of the ego vehicle would already be far from that of typical Fig. 5 shows an example how the algorithm works in the
vehicle-following system. After such a situation occurred, a absence of obstacles but with lanes. When the leader vehicle
new leader vehicle must be selected. slightly drives out of lane, the ego vehicle is guided back into
The same situations occur when the leader vehicle disappears the lane. No modification of the leader-vehicle path occurs in
from the field of view of the camera system. Control is returned the absence of obstacles and lanes.
to the driver, and a new leader vehicle must be selected. With 2) Simulation Results With Lateral Control: Collision
the use of car-to-car communication and GPS localization, one avoidance maneuvers are dangerous to conduct in the real
could circumvent this limitation. world. It is not safe to interfere with a car’s path when it
GEHRIG AND STEIN: COLLISION AVOIDANCE FOR VEHICLE-FOLLOWING SYSTEMS 241
Fig. 7. Traffic scene with a dredger at the right side of the street and with
counter traffic.
Fig. 6. Bird view for a situation where a pedestrian slightly enters the driving
corridor, which necessitates a swerve maneuver using a faster actuator. A
steering actuator with about 150-ms delay is used. The ego vehicle and the
leader drive at 10 m/s, and they are about 20 m apart. An avoidance maneuver
with a comfortable safety margin results.
Fig. 12. Bird view for a situation where the leader vehicle passes a bicycle
Fig. 9. Bird view for an actually driven situation where a pedestrian barely and the ego vehicle must avoid the bicycle not to cut it. The ego vehicle and
enters the driving corridor, which necessitates a swerve maneuver. The ego the leader vehicle drive at 8 m/s, and they are about 18 m apart. The snapshots
vehicle and the leader vehicle drive at 6 m/s, and they are about 15 m apart. show that the bicycle is avoided successfully.
Fig. 10. Snapshots for the scene depicted in Fig. 9, showing the swerve
maneuver in three steps. Fig. 13. Deviation plot for the scene in this figure. The frame number roughly
corresponds to the z position in the global reference frame (constant velocity
assumed). Compared to the image data, the cardboard box location is depicted
in the graph. Assuming the leader-vehicle path runs along the z axis at x = 0,
the deviation curve also shows the path of the ego vehicle.
brakes but overlaps slightly with the other lane. Hence, a swerve
maneuver of the autonomous vehicle will yield results similar
to a maneuver a human would conduct in such a situation.
In Fig. 12, the leader vehicle passes a bicyclist and cuts back
in too early for pure vehicle following. Due to the elastic-band
framework, enough room is left for the bicyclist. Fig. 12 shows
three snapshots of the scene that are 0.8-s apart each. The ego
vehicle leaves sufficient room for the bicyclist when returning
to its lane.
3) Real-World Results Using Stereo Vision: After extensive
tests with simulated obstacles, we performed avoidance maneu-
vers with real image processing data in the research vehicle. A
Fig. 11. Bird view for a situation where a car slightly enters the driving
correct mapping of the whole avoidance maneuver in an inertial
corridor, which necessitates a swerve maneuver. The ego vehicle and the leader reference frame is difficult to establish due to localization and
vehicle drive at 8 m/s, and they are about 18 m apart. measurement uncertainties. In our chosen scenario, a human as
a thin leader vehicle runs on a straight path at about 5 m/s.
In Fig. 11, the leader vehicle drives straight. Another vehicle A cardboard box is located next to that path. The ego vehicle
in the right lane recognizes an obstacle ahead and starts to has to avoid the box while following the human. Fig. 13 shows
change its lane. When recognizing the autonomous vehicle, it the deviation between leader vehicle and ego vehicle path. The
GEHRIG AND STEIN: COLLISION AVOIDANCE FOR VEHICLE-FOLLOWING SYSTEMS 243
Fig. 14. Avoidance scene with a human as a leader vehicle passing close to a
cardboard box on the left. Due to the larger width, the ego vehicle performs a
swerve maneuver to avoid the box. The elastic-band path is depicted projected
to the ground. The leader vehicle and the ego vehicle are about 12 m apart.
Fig. 16. Bird view for the scene in Fig. 15. The leader-vehicle path becomes
pushed toward a straight path, which is desirable for that scenario.