The Effectiveness of Sliding Mode Control for Robust Vision Stabilization under the Plant-Binding Condition
Authors: Sooyeun Yang, Jongseong Brad Choi, Seung Bok choi
Organizations: Department of Mechanical Engineering, SUNY Korea, Incheon, Republic of Korea · Department of Mechanical Engineering, Stony Brook University, NY, USA · Department of Computer Science, SUNY Korea, Incheon, Republic of Korea
Boundary-layer Sliding Mode Control (SMC) has been applied to vision-based stabilization, but identifying its activation condition against simpler causal baselines (LPF, PID) has been elusive. The operational condition is plant binding: the disturbance velocity approaches or exceeds the actuator slew limit, so the bounded per-step actuation budget binds. We validate this in two independent vision domains: handheld translation stabilization (12 1080p clips; LPF, PID, SMC, L1) and angular re-framing against a virtual slew-rate-limited pan-tilt-zoom (PTZ) plant. Outside binding, leave-one-out cross-validation makes SMC and LPF on translation statistically indistinguishable, and PID beats SMC on the angular 99th-percentile pointing offset by 5.85 degrees (95% CI clear of zero); inside binding -- reached only by sweeping the simulated slew limit, as both captured datasets land outside it -- the translation gap stays a tie and SMC beats PID on the angular worst case (Cohen's d up to +0.83). The PTZ plant's 100 degrees/s default sits on the cross-over, which explains a small-margin PID result previously reported in the angular setting. A complementary ablation shows raising the SMC reaching gain k costs mean tracking outside a narrow window.
Figures & tables
Figure 1: Block diagram of the unified per-axis control loop (both domains share the structure). A causal Butterworth split of the measured pose yields the intent reference xd and the shake d(t) , ∣d∣≤ε ; the plant imposes the per-step actuation budget vmaxΔt of ( 2 ); feedback closes on the applied (post-plant) pose. In the angular domain the estimation block is ArUco detection and the render block is PTZ pointing.
o|X[0.9,m,c]|X[0.9,m,c]|X[2.6,m,c]|Domain
Method
Configuration
Transl.
Raw
no processing
Transl.
LPF
4 th-order causal Butterworth, clip-specific fc
Transl.
PID
kp=120 , ki=15 , kd=25 , anti-windup [ 16 ]
Transl.
SMC
( 6 ): c=25 , k=10 , φ=2
Transl.
L1
global LP solve [ 10 ] ; non-causal
Angular
PID
Kp=1 , Ki=0 , Kd=0 (P-only in effect; Sec. 3.2 )
Table 1: Frozen controller configurations. Translation methods close the loop on the virtual unit-mass plant ( 1 ); angular methods on the slew-limited PTZ plant ( 2 ).
Table 2: Three-row decomposition of the translation σty gap (LPF − SMC), n=11 test clips. Row A is the paper-headline configuration; row B locks c=25 and frees only (k,φ) per LOO fold; row C frees all three.
Figure 2: Two-domain plant-binding cross-over. Left: paired σty(\textscLPF)−σty(\textscSMC) (px) on the 11 -clip test split as the translation actuator’s pixel slew vmax is swept from ∞ to 1 px/s. Right: paired offsetp99(\textscPID)−offsetp99(\textscSMC) (deg) on the 16 -cell angular grid as the PTZ slew is swept similarly. Shaded: 95% paired-bootstrap CIs. The PTZ 100∘/ s default (dashed red) sits at the right-panel zero-crossing.
Table 3: Metric-symmetry check. Paired offsetmean difference (PID − SMC) on the 16 -cell angular grid at representative slews. Inside the SMC-winning offsetp99 regime ( slew≤20∘/ s) SMC does not lose on the mean.
Figure 3: Gain-sweep ablation on the angular grid. Top: offsetmean vs. plant slew; SMC-jt ( k=400 ) loses to PID at every slew. Bottom: offsetp99 ; SMC-jt wins only near slew≈50∘/ s. Bands 95% paired-bootstrap CIs.
Sliding mode control uses switching feedback to drive systems toward designed surfaces and maintain robust behavior despite disturbances and uncertainty.
This paper presents a unified control framework for robust trajectory tracking and moving obstacle avoidance applicable to a broad class of mobile robots. By formulating a generalized kinematic transformation, we convert diverse vehicle dynamics into a strict feedback form, facilitating the design of a Sliding Mode Control (SMC) strategy for precise and robust reference tracking. To ensure operational safety in dynamic environments, the tracking controller is integrated with a Collision Cone Control Barrier Function (C3BF) based safety filter. The proposed architecture guarantees asymptotic tracking in the presence of external disturbances while strictly enforcing collision avoidance constraints. The novelty of this work lies in designing a sliding mode controller for ground robots like the Ackermann drive, which has not been done before. The efficacy and versatility of the approach are validated through numerical simulations and extensive real-world experiments on three distinct platforms: an Ackermann-steered vehicle, a differential drive robot, and a quadrotor drone. Video of the experiments are available at https://youtu.be/dWcxwum96vk
Shubham Sawarkar, P Sangeerth, S Saharsh +1
Centre for Cyber-Physical Systems and Department of Aerospace Engineering, Indian Institute of Science, Bengaluru, India. · Department of Aerospace Engineering, Indian Institute of Science, Bengaluru, India.
We propose VISION-SLS, a method for nonlinear output-feedback control from high-resolution RGB images which provides robust constraint satisfaction guarantees under calibrated uncertainty bounds despite partial observability, sensor noise, and nonlinear dynamics. To enable scalability while retaining guarantees, we propose: (i) a learned low-dimensional observation map from pretrained visual features with state-dependent error bounds, and (ii) a causal affine time-varying output-feedback policy optimized via System Level Synthesis (SLS). We develop a scalable, novel solver for the resulting nonconvex program that leverages sequential convex programming coupled with efficient Riccati recursions. On two simulated visuomotor tasks (a 4D car and a 10D quadrotor) with >= 512 x 512 pixels and a 59D humanoid task with partial observability, our method enables safe, information-gathering behavior that reduces uncertainty while guaranteeing constraint satisfaction with empirically-calibrated error bounds. We also validate our method on hardware, safely controlling a ground vehicle from onboard images, outperforming baselines in safety rate and solve times. Together, these results show that learned visual abstractions coupled with an efficient solver make SLS-based safe visuomotor output-feedback practical at scale. The code implementation of our method is available at https://github.com/trustworthyrobotics/VISION-SLS.
Antoine P. Leeman, Shuyu Zhan, Melanie N. Zeilinger +1
Institute for Dynamic Systems and Control, ETH Zürich · Georgia Institute of Technology, Schools of 2Interactive Computing, 3Aerospace Engineering
In this paper, we consider the problem of regulating and maintaining a target formation characterized by a set of bidirectional bearing constraints under disturbances. The agents in the formation are modeled by single integrators with deterministic bounded continuous disturbances of which both actual function and upper bound are unavailable for the control design. Due to the time-varying disturbances, the target formation is time-varying. We propose displacement/bearing-only based adaptive sliding mode control laws to uniformly asymptotically stabilize the time-varying target formation and reject the matched disturbances, and provide sufficient conditions to prevent possible collisions. A time-dependent adaptive design method is provided to convert the displacement-based control law to a bearing-only one. In addition, to alleviate chattering phenomena from sliding mode control, smooth adaptive control laws are introduced to guarantee uniform global boundedness of the desired formation. Finally, simulation results are given to support the analysis.
Minh Hoang Trinh, Chuong Van Nguyen, Quoc Van Tran +1
East Asia University of Technology, Hanoi, Vietnam · Viterbi School of Engineering – Department of Aerospace and Mechanical Engineering, University of Southern California, CA, USA · Ghost Robotics, Philadelphia, PA, USA +2