High-Speed Forward and Reverse Tractor-Trailer Driving with Learned Vehicle Dynamics
Authors: Aaron Chen, David Shen, Taekyung Kim, Kaleb Ben Naveed, Dimitra Panagou
Organizations: Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, 48109, USA · Department of Robotics, University of Michigan, Ann Arbor, MI, 48109, USA · Department of Aerospace Engineering, University of Michigan, Ann Arbor, MI, 48109, USA
Tractor-trailer systems are difficult to control, especially unstable during reverse motion, and their dynamics depend on difficult-to-measure factors, including road friction and suspension coefficients. We introduce a learned dynamics model for tractor-trailer control and compare it with a reduced-order dynamics model with Fiala tire forces as an analytic baseline. Specifically, we compare a model predictive path integral (MPPI) controller that uses the learned dynamics model to an MPPI controller that uses the analytic model, as well as to three additional baseline controllers. In the main closed-loop tracking experiments across four simulated environments, MPPI with learned dynamics achieves mean speeds closer to the target magnitudes and lower root-mean-square (RMS) hitch angles than MPPI with the analytic model at every tested setpoint, with higher completion rates in seven of eight reverse configurations.
Figures & tables
Fig. 1: Illustration of our tractor-trailer model. The tractor is approximated by a bicycle model and the trailer by a single axle connected to the tractor at a common hitch point.
Fig. 2: Overview of our controller architecture. MPPI uses a multilayer perceptron (MLP) trained offline to predict dynamic-state and actuator rates from a sliding window of state-action pairs. These predictions are integrated recursively to generate candidate trajectories for receding-horizon control.
Fig. 3: Top-down view of the Snow + Slope test environment, based on the Circuit de Barcelona-Catalunya layout. Snow patches and terrain changes are applied to the base asphalt track. The snow pattern matches the Snow environment, and the terrain profile matches the Slope environment.
Fig. 4: Representative reverse-driving trajectories of Controller 1 in (a) Asphalt, (b) Snow, (c) Slope, and (d) Snow + Slope. White patches indicate snow-covered regions with lower friction.
Parameter
Forward
Reverse
kv
1×102
5×101
kc
1×100
5×101
ka
7×102
1×102
λ (temperature)
150
100
diag(Σ)
(7×10−2,0.2)
(2×10−2,0.2)
K (samples)
500
500
TABLE I: MPPI settings for the main tracking experiments. Sampling covariance is expressed in normalized command coordinates (uδ,ua) .
Asphalt
Snow
Slope
Snow + Slope
Controller
v⋆
vˉ
αˉrms
Nˉ
C/J/S/O/F
vˉ
αˉrms
Nˉ
C/J/S/O/F
vˉ
αˉrms
Nˉ
C/J/S/O/F
vˉ
αˉrms
Nˉ
C/J/S/O/F
(km/h)
(km/h)
(deg)
(steps)
(out of 9)
(km/h)
(deg)
(steps)
(out of 9)
(km/h)
(deg)
(steps)
(out of 9)
(km/h)
(deg)
(steps)
(out of 9)
1: Ours
−30
29.1
1.14
500
9/0/0/0/0
29.1
1.18
500
9/0/0/0/0
25.4
1.03
455
8/0/1/0/0
20.4
10.82
386
6/0/3/0/0
−50
47.2
1.75
500
9/0/0/0/0
46.0
1.82
500
9/0/0/0/0
42.1
3.06
498
8/1/0/0/0
30.4
15.41
413
4/0/5/0/0
80
75.4
2.57
500
9/0/0/0/0
72.6
2.72
500
9/0/0/0/0
70.7
2.67
500
9/0/0/0/0
69.1
2.83
500
9/0/0/0/0
2: MPPI (analytic) [ 7 ]
−30
19.7
5.25
392
5/0/4/0/0
19.6
7.82
403
5/0/4/0/0
22.3
2.86
498
8/0/1/0/0
16.7
11.47
365
4/0/5/0/0
TABLE II: Closed-loop tracking across four environments, with nine runs per configuration. Controllers are defined in Section IV-A . Bold hitch-angle values are the lowest for each velocity setpoint and environment.
Fig. 5: Five-second open-loop dynamics predictions in Snow + Slope for forward (a,b,c) and reverse (d,e,f) driving. The measured trajectory is shown in dotted black, and the dynamics models’ open-loop predictions are shown in solid color. Terminal tractor and trailer poses are denoted by solid and hollow boxes, respectively. The blue shading denotes snow patches with decreased friction, and elevation contours are spaced at 5 m.
Analytic
Friction-aware analytic
Learned
Direction
Environment
ep
eα
ep
eα
ep
eα
Reverse
Asphalt
5.8
96.5
7.4
113.0
4.2
101.1
Snow
7.0
130.1
4.9
107.9
4.0
88.2
Slope
7.7
132.6
8.2
134.2
2.2
78.7
Snow + Slope
8.1
131.5
7.3
111.6
2.1
83.4
Forward
Asphalt
7.3
93.4
6.6
95.3
1.4
2.1
TABLE III: Position ( ep ) and wrapped hitch-angle ( eα ) RMSE for one five-second segment per direction and environment (meters and degrees, respectively). Bold values indicate the lowest RMSE for each environment, direction, and metric.
Predictor
v⋆
vˉ
αˉrms
Nˉ
C/J/S/O/F
(km/h)
(km/h)
(deg)
(steps)
(out of 3)
H=1
−30
15.8
29.29
98
0/3/0/0/0
80
48.0
22.27
278
0/2/0/1/0
H=4
−30
30.0
2.84
500
3/0/0/0/0
80
51.6
29.29
345
0/3/0/0/0
H=8
−30
30.9
2.87
500
3/0/0/0/0
TABLE IV: Closed-loop history comparison on Snow + Slope.
Research Institute for Signals, Systems and Computational Intelligence, sinc(i), FICH-UNL/CONICET, Ciudad Universitaria UNL, 4◦piso FICH, (S3000) Santa Fe, Argentina.
Department of Mechanical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands. · Safety & Driver Controls Group, Vehicle Development, DAF Trucks N.V., Eindhoven, The Netherlands.