REVIEW 4 major objections 5 minor 29 references
LLMs-guided adaptive compensator: Bringing Adaptivity to Automatic Control Systems with Large Language Models
T0 review · 4 major / 5 minor · reviewed 2026-08-15 · deepseek-v4-flash
Pith's one-line read An LLM, prompted only with reference and observed responses, can iteratively synthesize a compensator that makes an unknown robot match a reference response, outperforming classical adaptive controllers without system identification.
desk verdict A promising LLM-compensator idea undermined by an invalid Lyapunov proof and overclaimed 'zero-shot' real-world validation. read the letter →
The pith
A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.
The reading
What carries the argument
The central object is the LLM-guided adaptive compensator, a function $\phi_c(\cdot)$ produced by the LLM and added to a fixed feedback controller. The machinery that carries the argument is the closed interaction loop $\phi_c^{(i+1)}=\phi_c^{(i)}+L(y^{(i)}(t))$, where $L$ maps the prompt space—natural-language task description, reference response, observed response—to a compensator expression, together with the Lyapunov analysis of the resulting error dynamics. In the worked example the compensator takes the explicit form $u_{\mathrm{comp}}=k_p e_1+(k_d+k_v)e_2+k_i I$, and the stability proof uses $V=\frac{1}{2}(e_1^2+e_2^2)$, whose derivative $\dot{V}=e_1e_2-be_2u_{\mathrm{comp}}+e_2\Delta_{\mathrm{fixed}}$ is bounded via the triangle inequality to yield regional convergence conditions $1.02e_1+e_2>15$ for $e_2>0$ and $1.02e_1+e_2<-15$ for $e_2<0$.
What would settle it
On the real PAM prototype, inject a disturbance that pushes the compensated error state outside the region $1.02e_1+e_2>15$ for $e_2>0$ and observe whether the system returns to the reference; failure to recover would falsify the regional-stability claim. A second check is to run the identical zero-shot prompt on a new plant that satisfies the affine structure with different $A$ and $B$; if the compensator does not converge, the claimed generalizability fails.
Extended reading notes
Core claim
The paper's central claim is that the role of an adaptive controller—keeping an uncertain plant tracking a desired behavior—can be delegated to a large language model as a compensator-design task. The user first fixes a reference system with known dynamics and a fixed, well-tuned controller, and records its response. The LLM is then prompted with that reference response, the unknown system's observed response, and natural-language instructions, and returns a compensator $\phi_c$ that augments the existing control input, $u(t)=u_0(t)+\phi_c(y_{\mathrm{desired}},y(t),y_r(t),k)$. Each round the updated response is fed back and the compensator is revised via $\phi_c^{(i+1)}=\phi_c^{(i)}+\Delta^{(i)}$, with $\Delta^{(i)}=L(y^{(i)}(t))$. In the central experiments the compensator produced smooth, low-overshoot tracking on a 1- and 2-DoF McKibben pneumatic-artificial-muscle arm and aligned a simulated humanoid shoulder response to the real robot's response, outperforming the four classical or learning-based alternatives while eliminating explicit modeling and manual gain tuning. The accompanying Lyapunov argument uses $V=\frac{1}{2}(e_1^2+e_2^2)$ to show regional asymptotic stability for unknown systems whose error dynamics fit $\dot{x}=Ax+Bu+d(t)$ with bounded disturbance, and the reasoning-path traces show the LLM diagnosing the plant from response features (overshoot, settling time, steady-state error) rather than deriving symbolic control laws.
Load-bearing premise
The argument stands on the premise that the real robot's behavior is close enough to the affine state-space form $\dot{x}=Ax+Bu$ with a bounded disturbance, and that the tracking error stays inside the derived regional set; the paper does not verify either condition for the pneumatic-arm or humanoid platforms, and its own Unknown System 3 shows that a plant violating the structure is not compensated.
Editorial extensions
If this is right
- Legacy robots can be made adaptive by adding an LLM-generated compensator on top of the existing controller without replacing the control loop; the humanoid experiment shows this works even when only the target angle, not the torque, can be modified.
- Controller design effort shifts from modeling and Lyapunov derivation to prompt construction and iterative response-based refinement; the paper's Table III reports higher success rates with fewer iterations for the compensator than for an LLM asked to design the whole adaptive controller.
- The compensator generalizes across nonlinear, time-varying unknown systems as long as their error dynamics share the affine structure of Eq. (20); the convergence region contracts as the discrepancy with the reference grows.
- On the 2-DoF PAM arm, compensating the harder second joint does not degrade the first joint, indicating task-aware decoupling across coupled soft actuators.
- Compared with replacing a control stack by a vision-language-action model, prompt-driven compensation is lightweight and non-intrusive, a practical route for already-deployed platforms.
Reading between the lines
- Because the iteration $\phi_c^{(i+1)}=\phi_c^{(i)}+L(y^{(i)})$ has no convergence proof, the practical guarantee rests on the LLM's prompt-following behavior; sweeping models, prompt phrasings, and initial compensators would show how often the loop actually converges.
- The generated compensator in the worked example is PID-like, so part of the gain may come from the fixed structure plus LLM-chosen coefficients; benchmarking against an optimally tuned fixed-gain PID would isolate the LLM's added value.
- The regional-stability analysis could be sharpened into an explicit robustness radius—bounds on $\|A_u-A_r\|$, $\|B_u-B_r\|$, and the disturbance magnitude—that predicts when a compensator will work, instead of a single numeric example.
- For the humanoid, compensation through target-angle correction adds a nonlinear mapping that likely explains the early oscillations; testing the same framework with direct torque access would separate interface constraints from methodological limits.
Signed reviews
Editorial analysis
A structured set of objections, weighed in public.
Referee Report
Summary. The paper proposes an LLM-guided adaptive compensator framework in which a large language model is prompted with the observed response of an unknown system and the response of a reference system, and returns a compensator (Eq. (5): u_comp = kp e1 + (kd + kv) e2 + ki I) that augments an existing fixed controller. The method is tested on a McKibben PAM-driven arm and a Unitree humanoid, in both simulation and hardware, and compared with a direct model-based adaptive controller, an MRAC, a learning-based G-PID controller, and an LLM-guided adaptive controller. The authors report superior tracking performance and lower design effort for their compensator, and support the claims of generalizability, adaptability, and robustness with a Lyapunov-based analysis in Section III and with reasoning-path inspections in Section V-B.
Significance. If the claims were valid, this would be a notable advance: it would demonstrate an LLM-generated compensator, obtained without system identification and with minimal tuning, that outperforms classical adaptive controllers on real soft and humanoid robots. The paper deserves credit for including real-robot experiments, several baseline comparisons, and an explicit attempt to analyze the LLM's reasoning path. However, the central theoretical pillar, the Lyapunov-based generalization analysis, contains a load-bearing algebraic error, and the algorithmic description conflicts with the 'zero-shot' claim used to justify generality. As a result, the paper's main conclusions about generalizability, adaptability, and robustness are not established by the presented analysis. The experimental results are promising but do not, by themselves, support the broad theoretical statements made in the abstract and conclusion.
major comments (4)
- [Section III, Eq. (15) and Eqs. (16)-(19)] The Lyapunov derivative is not correctly derived. Eq. (12) gives Vdot = e1*e2 - b*e2*u_comp + e2*Delta_fixed, but Eq. (15) replaces Delta_fixed by |Delta_fixed| without conditioning on the sign of e2. For e2 < 0 this replacement is not an upper bound on e2*Delta_fixed. More seriously, the case analysis in Eqs. (16)-(19) requires 19*e1 + 18.5*e2 + I > 274.45 when e2 > 0 and < -274.45 when e2 < 0. These conditions are violated in every neighborhood of the error origin, so the claimed 'regional asymptotic stability' is not established; Lyapunov's theorem requires Vdot < 0 in a punctured neighborhood of the origin. A direct substitution into Eq. (10) with Unknown System 1, reference state zero, e1 = -epsilon, e2 = epsilon, I = 0, u_base = 0, and d = 0 gives e2dot approximately 3.5*epsilon and Vdot approximately 2.5*epsilon^2 > 0 for arbitrarily small epsilon. Thus the central theoretical claim, and the generalizability/robustness conclusions that rest on it, are unsupported.
- [Section III, Eqs. (14)-(17)] The bound |Delta_fixed| <= 274.45 is asserted without derivation, and the substitution b = 1 is unjustified. Eq. (7) only states 0 <= b <= 4, while Eq. (15) uses b = 1. A valid worst-case bound on Delta_fixed requires explicit uniform bounds on x1,u, x2,u, x1,r, x2,r, u_base, u_r, and d(t) along the closed-loop trajectories; no such bounds are provided. The half-plane conditions Eqs. (16)-(19) also drop the integral term I without giving a bound on it, even though I appears in the same conditions. Without these bounds, the numeric constant 274.45 and the derived convergence region are meaningless.
- [Section II-A and Section III] The paper describes an iterative refinement procedure, phi_c^(i+1) = phi_c^(i) + Delta^(i) with Delta^(i) = L(y^(i)(t)), and Section V-A reports multiple refinement rounds, yet Section III and the conclusion describe the design as 'zero-shot' and use that characterization to argue generality. A compensator that is iteratively refined using the observed responses of the target system is fitted to that platform, not generated zero-shot. The 'zero-shot' terminology and the generality argument based on it are therefore contradicted by the method itself. This also undermines the claim that the final compensator requires no system-specific tuning or design effort.
- [Section III, Eq. (20)] The statement that the compensator remains effective for any system whose error dynamics 'closely align' with Eq. (1), regardless of whether A and B are linear or time-invariant, is not supported by the analysis. The proof treats only two specific second-order systems with b in [0,4]; no common Lyapunov function is exhibited for a class of systems, and no quantitative relationship between the size of the dynamic discrepancy and the size of the convergence region is derived. The real test platforms (PAM arm, humanoid) are not shown to satisfy Eq. (20) or the bounds used in the proof, so the theoretical generalization to those platforms is unsubstantiated.
minor comments (5)
- [Section III] There is a typo: 'generability' should be 'generalizability'. There are also typos elsewhere, e.g., 'prototytpe', 'adapitve', and 'T rends' in the figure caption.
- [Section V-A, Table III] The success-rate/iteration-count entries such as '80% / 5.4' are ambiguous. Please report the number of trials, the success criterion, and measures of variance, since the text mentions repeated trials but no statistics are given.
- [Section II-B] The subsection title 'LLMs-guided for adaptive controller' does not match the content; the content describes an LLM that directly designs an adaptive controller. Please align the terminology with the rest of the paper.
- [Section III, Eq. (5)] The integral variable I is described as the time integral of the tracking error, but the integration limits and the treatment of I in the Lyapunov analysis are not defined. Since I appears in the stability conditions, this needs to be specified.
- [Section IV] The LLM model name/version, prompt templates, and temperature/sampling settings are not disclosed, which prevents replication. These should be provided in an appendix or supplementary material, especially because the method's performance depends critically on the LLM's responses.
Circularity Check
Iterative response-fitting is relabeled as zero-shot prompting, so the generalizability claim is partially circular.
-
fitted input called prediction
[Section II.A 'Compensator Design' (update rule) and Section III 'Lyapunov-based Generalization Analysis' (zero-shot claim)]
"After each round of control execution (indexed by i), the updated system response y^(i)(t) from the unknown system is returned to the user. ... This process forms a closed-loop interactive cycle, where the compensator is iteratively improved across rounds. The update rule can be formalized as: ϕ(i+1)c = ϕ(i)c + ∆(i), ∆(i) := L(y(i)(t)) ... The compensator was generated solely through zero-shot prompting—without relying on predefined control templates, handcrafted structures, or manual tuning."
The final compensator is constructed by iterative updates whose inputs are the observed responses y^(i)(t) of the very unknown system later used for evaluation. The paper nevertheless labels the design 'zero-shot' and uses success on those systems to conclude 'strong generalizability, adaptability, and robustness.' This turns a fitted quantity into a prediction: the evaluation response is an input to the generation loop, so matching it is by construction rather than independent evidence of generalization. The only genuine out-of-distribution evaluation is the humanoid 50°→80° test with altered gains; the blanket zero-shot claim is not supported by the closed-loop interactive fitting protocol.
full rationale
The concrete circularity is the gap between the closed-loop iterative fitting protocol and the 'zero-shot'/generalizability claim. The compensator update rule feeds observed responses of the target system back into the LLM, so the final compensator is a function of the evaluation data; using success on those same systems as evidence of strong generalizability is a fitted-input-called-prediction step. The paper does include genuine out-of-distribution checks (humanoid 80° test and some novel systems in Figure 3), so the circularity is partial rather than total. The Lyapunov derivation issue in Eqs. (10)-(19) is an internal correctness problem—the sign error and the stability region excluding the origin—rather than a circularity, so it is not counted in the score. Self-citations [23], [26]-[28] are used for plant models and baselines, but the central claim does not reduce to them.
Assumptions & free parameters
free parameters (5)
- LLM-generated compensator gains kp, kd, kv, ki =
kp=20.0, kd=10.0, kv=8.5, ki=1.0
- Reference system matrix A = [[0,1],[-5,-3]] =
A = [[0,1],[-5,-3]]
- SMC gains lambda, k, gamma =
not stated numerically
- Humanoid PD gains (250,30) and test (50,8) =
(250,30), (50,8)
- Disturbance bound 274.45 =
274.45
assumptions (5)
- domain assumption The unknown system can be written as x_dot = A x + B u with bounded additive disturbance (Eq. (20) and (7))
- domain assumption The compensator structure generated by the LLM is a PID on tracking error (Eq. (5))
- ad hoc to paper The user-LLM iterative refinement converges to a satisfactory compensator within a few rounds
- domain assumption The LLM is a reliable nonlinear mapping L from prompts to compensators, using pre-trained knowledge of control principles
- standard math Lyapunov's second method is applicable with the given positive definite V
Cite this review
Pith. "Pith review of LLMs-guided adaptive compensator: Bringing Adaptivity to Automatic Control Systems with Large Language Models." pith.science (2026). https://pith.science/paper/XFXTQNJ6
@misc{pith2026250720509,
author = {Pith},
title = {Pith review of: LLMs-guided adaptive compensator: Bringing Adaptivity to Automatic Control Systems with Large Language Models},
year = {2026},
howpublished = {\url{https://pith.science/paper/XFXTQNJ6}},
note = {Machine review of arXiv:2507.20509}
}
read the original abstract
With rapid advances in code generation, reasoning, and problem-solving, Large Language Models (LLMs) are increasingly applied in robotics. Most existing work focuses on high-level tasks such as task decomposition. A few studies have explored the use of LLMs in feedback controller design; however, these efforts are restricted to overly simplified systems, fixed-structure gain tuning, and lack real-world validation. To further investigate LLMs in automatic control, this work targets a key subfield: adaptive control. Inspired by the framework of model reference adaptive control (MRAC), we propose an LLM-guided adaptive compensator framework that avoids designing controllers from scratch. Instead, the LLMs are prompted using the discrepancies between an unknown system and a reference system to design a compensator that aligns the response of the unknown system with that of the reference, thereby achieving adaptivity. Experiments evaluate five methods: LLM-guided adaptive compensator, LLM-guided adaptive controller, indirect adaptive control, learning-based adaptive control, and MRAC, on soft and humanoid robots in both simulated and real-world environments. Results show that the LLM-guided adaptive compensator outperforms traditional adaptive controllers and significantly reduces reasoning complexity compared to the LLM-guided adaptive controller. The Lyapunov-based analysis and reasoning-path inspection demonstrate that the LLM-guided adaptive compensator enables a more structured design process by transforming mathematical derivation into a reasoning task, while exhibiting strong generalizability, adaptability, and robustness. This study opens a new direction for applying LLMs in the field of automatic control, offering greater deployability and practicality compared to vision-language models.
Figures
Figures from the paper (5 more)
Reference graph
Works this paper leans on
-
[1]
A survey on large language models for code generation,
J. Jiang, F. Wang, J. Shen, S. Kim, and S. Kim, “A survey on large language models for code generation,” arXiv preprint arXiv:2406.00515, 2024
arXiv 2024
-
[2]
Large lan- guage models for mathematical reasoning: Progresses and challenges,
J. Ahn, R. Verma, R. Lou, D. Liu, R. Zhang, and W. Yin, “Large lan- guage models for mathematical reasoning: Progresses and challenges,” arXiv preprint arXiv:2402.00157 , 2024
arXiv 2024
-
[3]
Chain-of-thought prompting elicits reasoning in large language models,
J. Wei, X. Wang, D. Schuurmans, M. Bosma, F. Xia, E. Chi, Q. V . Le, D. Zhou, et al. , “Chain-of-thought prompting elicits reasoning in large language models,” Advances in neural information processing systems , vol. 35, pp. 24824–24837, 2022
2022
-
[4]
Large language models for robotics: A survey,
F. Zeng, W. Gan, Y . Wang, N. Liu, and P. S. Yu, “Large language models for robotics: A survey,” arXiv preprint arXiv:2311.07226 , 2023
arXiv 2023
-
[5]
Enhancing the llm-based robot manipulation through human-robot collaboration,
H. Liu, Y . Zhu, K. Kato, A. Tsukahara, I. Kondo, T. Aoyama, and Y . Hasegawa, “Enhancing the llm-based robot manipulation through human-robot collaboration,” arXiv preprint arXiv:2406.14097 , 2024
arXiv 2024
-
[6]
Vision-language- action models: Concepts, progress, applications and challenges,
R. Sapkota, Y . Cao, K. I. Roumeliotis, and M. Karkee, “Vision-language- action models: Concepts, progress, applications and challenges,” arXiv preprint arXiv:2505.04769, 2025
arXiv 2025
-
[7]
Vima: General robot manipulation with multimodal prompts,
Y . Jiang, A. Gupta, Z. Zhang, G. Wang, Y . Dou, Y . Chen, L. Fei-Fei, A. Anandkumar, Y . Zhu, and L. Fan, “Vima: General robot manipulation with multimodal prompts,” arXiv preprint arXiv:2210.03094 , vol. 2, no. 3, p. 6, 2022
-
[8]
pi0: A vision-language-action flow model for general robot control,
K. Black, N. Brown, D. Driess, A. Esmail, M. Equi, C. Finn, N. Fusai, L. Groom, K. Hausman, B. Ichter, et al., “pi0: A vision-language-action flow model for general robot control,” arXiv preprint arXiv:2410.24164 , 2024
arXiv 2024
Show all 29 references
-
[9]
Gemini robotics: Bringing ai into the physical world,
G. R. Team, S. Abeyruwan, J. Ainslie, J.-B. Alayrac, M. G. Arenas, T. Armstrong, A. Balakrishna, R. Baruch, M. Bauza, M. Blokzijl, et al., “Gemini robotics: Bringing ai into the physical world,” arXiv preprint arXiv:2503.20020, 2025
2025 arXiv
-
[10]
Albertos and I
P. Albertos and I. Mareels, Feedback and control for everyone , vol. 1. Springer, 2010
2010
-
[11]
Capabilities of large language models in control engineering: A benchmark study on gpt-4, claude 3 opus, and gemini 1.0 ultra,
D. Kevian, U. Syed, X. Guo, A. Havens, G. Dullerud, P. Seiler, L. Qin, and B. Hu, “Capabilities of large language models in control engineering: A benchmark study on gpt-4, claude 3 opus, and gemini 1.0 ultra,” arXiv preprint arXiv:2404.03647 , 2024
2024 arXiv
-
[12]
Controlagent: Automating control system design via novel integration of llm agents and domain expertise,
X. Guo, D. Keivan, U. Syed, L. Qin, H. Zhang, G. Dullerud, P. Seiler, and B. Hu, “Controlagent: Automating control system design via novel integration of llm agents and domain expertise,” arXiv preprint arXiv:2410.19811, 2024
-
[13]
Agenticcontrol: An automated con- trol design framework using large language models,
M. Narimani and S. A. Emami, “Agenticcontrol: An automated con- trol design framework using large language models,” arXiv preprint arXiv:2506.19160, 2025
2025 arXiv
-
[14]
Smartcontrol: Interactive pid controller design powered by llm agents and control system expertise,
K. Tohma, H. ˙I. Okur, H. G ¨ursoy-Demir, M. N. Aydın, and C. Yero ˘glu, “Smartcontrol: Interactive pid controller design powered by llm agents and control system expertise,” SoftwareX, vol. 31, p. 102194, 2025
2025
-
[15]
Sastry and M
S. Sastry and M. Bodson, Adaptive control: stability, convergence and robustness. Courier Corporation, 2011
2011
-
[16]
Online self-tuning mechanism for direct adaptive control of tall building,
A. Hosseini and T. Taghikhany, “Online self-tuning mechanism for direct adaptive control of tall building,” International Journal of Adaptive Control and Signal Processing , vol. 32, no. 3, pp. 424–446, 2018
2018
-
[17]
Indirect adaptive control using neural network and discrete extended kalman filter for wheeled mobile robot,
M. Y . Silaa, A. Bencherif, and O. Barambones, “Indirect adaptive control using neural network and discrete extended kalman filter for wheeled mobile robot,” in Actuators, vol. 13, p. 51, MDPI, 2024
2024
-
[18]
A lyapunov-based direct adaptive controller for the suppres- sion and synchronization of a perturbed nuclear spin generator chaotic system,
I. Ahmad, “A lyapunov-based direct adaptive controller for the suppres- sion and synchronization of a perturbed nuclear spin generator chaotic system,” Applied Mathematics and Computation , vol. 395, p. 125858, 2021
2021
-
[19]
Adaptive human-robot collaboration control based on optimal admittance parameters,
X. Yu, J. Wu, C. Xu, H. Luo, and L. Ou, “Adaptive human-robot collaboration control based on optimal admittance parameters,” Journal of Shanghai Jiaotong University (Science) , vol. 27, no. 5, pp. 589–601, 2022
2022
-
[20]
Llm-controller: Dynamic robot control adaptation using large language models,
R. Zahedifar, M. S. Baghshah, and A. Taheri, “Llm-controller: Dynamic robot control adaptation using large language models,” Robotics and Autonomous Systems , vol. 186, p. 104913, 2025
2025
-
[21]
Adaptive model selection,
X. Shen and J. Ye, “Adaptive model selection,” Journal of the American Statistical Association , vol. 97, no. 457, pp. 210–221, 2002
2002
-
[22]
Safety-critical adaptive control with nonlinear reference model systems,
E. Arabi, K. Garg, and D. Panagou, “Safety-critical adaptive control with nonlinear reference model systems,” in 2020 American Control Conference (ACC), pp. 1749–1754, IEEE, 2020
2020
-
[23]
A gan based pid controller for highly adaptive control of a pneumatic-artificial-muscle driven antagonistic joint,
Z. Zhou, Y . Lu, S. Kokubu, P. E. Tort ´os, and W. Yu, “A gan based pid controller for highly adaptive control of a pneumatic-artificial-muscle driven antagonistic joint,” Complex & Intelligent Systems , vol. 10, no. 5, pp. 6231–6248, 2024
2024
-
[24]
Mrac revisited: guaranteed perfor- mance with reference model modification,
V . Stepanyan and K. Krishnakumar, “Mrac revisited: guaranteed perfor- mance with reference model modification,” in Proceedings of the 2010 American Control Conference , pp. 93–98, IEEE, 2010
2010
-
[25]
Strict lyapunov functions for model reference adaptive control: Application to lagrangian systems,
A. Lor ´ıa, E. Panteley, and M. Maghenem, “Strict lyapunov functions for model reference adaptive control: Application to lagrangian systems,” IEEE Transactions on Automatic Control , vol. 64, no. 7, pp. 3040–3045, 2018
2018
-
[26]
The role of pre-tensioned springs in 3 pneumatic artificial muscles driven joint mechanisms with sliding mode controllers,
Z. Zhou, Y . Wang, and W. Yu, “The role of pre-tensioned springs in 3 pneumatic artificial muscles driven joint mechanisms with sliding mode controllers,” Robotics and Autonomous Systems , vol. 151, p. 104017, 2022
2022
-
[27]
A simulation study on model reference adaptive trajectory controller for back stretchable mckibben pneumatic artificial muscles,
Z. Zhou, S. Mao, W. Yu, and L. He, “A simulation study on model reference adaptive trajectory controller for back stretchable mckibben pneumatic artificial muscles,” in 2024 17th International Convention on Rehabilitation Engineering and Assistive Technology (i-CREATe), pp. 1–...
2024
-
[28]
Optimization of spring constant of a pneumatic artificial muscle-spring driven antagonistic structure,
Z. Zhou, S. Kokubu, Y . Wang, Y . Lu, P. E. Tort ´os, and W. Yu, “Optimization of spring constant of a pneumatic artificial muscle-spring driven antagonistic structure,” IEEE Robotics and Automation Letters , vol. 7, no. 3, pp. 5982–5989, 2022
2022
-
[29]
Fixed-time angle tracking control for multi-dof manipulator driven by pneumatic artificial muscles,
X. Liu, X. Zhang, F. Xu, S. Gu, and J. Zhang, “Fixed-time angle tracking control for multi-dof manipulator driven by pneumatic artificial muscles,” IEEE Transactions on Industrial Electronics , 2024
2024
Reviewed August 15, 2026 · model on record in the stance chip above.
Discussion (0). Continue with ORCID to comment.