Stability-Aligned Residual Adaptation for Rapid Recovery from Dynamics Shifts

Nethmi Jayasinghe; Diana Gontero; Francesco Migliarba; Spencer T. Brown; Vinod K. Sangwan; Mark C. Hersam; Amit Ranjan Trivedi

cs.ROMar 8, 2026

Stability-Aligned Residual Adaptation for Rapid Recovery from Dynamics Shifts

Authors: Nethmi Jayasinghe, Diana Gontero, Francesco Migliarba, Spencer T. Brown, Vinod K. Sangwan, Mark C. Hersam, Amit Ranjan Trivedi

Organizations: Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL, USA. · Department of Neurobiology, Northwestern University, Evanston, IL, USA. · Department of Materials Science and Engineering, Northwestern University, Evanston, IL, USA. · Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL, USA. ·

Abstract

Robotic systems deployed beyond controlled environments encounter abrupt and unobserved dynamics shifts that induce substantial transient performance loss, even when the nominal closed loop remains locally stabilizing. We formulate rapid inference-time recovery for physical AI as a constrained residual learning problem, in which an online correction added to a frozen reinforcement learning policy is regulated to minimize recovery time while remaining inside the robustness margin of the nominal controller. We specifically focus upon the regulation of residual's corrective authority relative to an already competent frozen policy. The learned residual produces bounded action-space corrections online, and a Stability Alignment Gate regulates this corrective authority through magnitude constraints, directional coherence, performance-conditioned regulation, and adaptive gain modulation. The method requires no environment resets, policy retraining, explicit system identification, or privileged shift information. Across mid-episode changes in actuation, mass, and contact conditions, it reduces recovery time relative to frozen SAC by up to 87% on Go1, 48% on Cassie, 30% on H1, and 20% on Scout in simulation, while preserving near-nominal steady-state performance. The framework is also characterized on two physical robots, a Trossen ViperX manipulator and an AgileX Scout Mini, cutting recovery time by 19.5% on hardware without modifying onboard controller or accessing shift information.

Figures & tables

Figure 1: Overview of authority-regulated residual adaptation. (a) A frozen RL policy generates nominal actions, while a parallel residual channel learns online corrections from tracking errors; the Stability Alignment Gate (SAG) regulates their injection before forming the final action. (b) Residual inputs pass through a fixed feature expansion, transient filtering, and fast and slow per-joint heads. Task-error and performance signals modulate the online residual update and the corrective authority, while SAG enforces magnitude bounds, directional coherence, performance-conditioned regulation, and adaptive gain regulation.

Group	Method	Actuator Degradation (0.76 $\times$ )				Mass Increase (1.15 $\times$ )				Friction Increase (2.1 $\times$ )
		AUC $\uparrow$	SSR $\uparrow$	TTR-50 $\downarrow$	TotalR $\uparrow$	AUC $\uparrow$	SSR $\uparrow$	TTR-50 $\downarrow$	TotalR $\uparrow$	AUC $\uparrow$	SSR $\uparrow$	TTR-50 $\downarrow$	TotalR $\uparrow$
No Adapt	SAC-Only	0.437	0.427	$\geq 4500$	9562 $\pm$ 122	1.001	1.001	1950	18411 $\pm$ 104	0.934	0.933	$\geq 4500$	17233 $\pm$ 115
Online	SAC + Ours	0.664	0.666	3962	13520 $\pm$ 150	1.042	1.044	168	20150 $\pm$ 295	0.973	0.965	189	18783 $\pm$ 143
	SAC+MRAC	0.372	0.392	2442	8439 $\pm$ 3719	0.908	0.904	2929	17778 $\pm$ 1498	0.496	0.445	4361	10595 $\pm$ 1807
	SAC+RLS	0.402	0.462	2230	8961 $\pm$ 3443	0.918	0.912	2553	17957 $\pm$ 1619	0.529	0.443	4102	11164 $\pm$ 3447
	Online SAC	0.384	0.243	3802	8651 $\pm$ 3511	0.716	0.558	3813	14432 $\pm$ 3159	0.432	0.325	4356	9470 $\pm$ 2450

Table 1: Go1 recovery performance under representative perturbations. Metrics include recovery AUC, SSR, TTR-50, and total return (mean

\pm

std over 30 trials). Higher is better for AUC, SSR, and total return; lower is better for TTR-50.

		Agility Cassie						Unitree H1
		Mass (1.15 $\times$ )			Friction (1.4 $\times$ )			Mass (1.15 $\times$ )			Friction (1.3 $\times$ )
Group	Method	SSR $\uparrow$	TTR-50 $\downarrow$	TotalR $\uparrow$	SSR $\uparrow$	TTR-50 $\downarrow$	TotalR $\uparrow$	SSR $\uparrow$	TTR-50 $\downarrow$	TotalR $\uparrow$	SSR $\uparrow$	TTR-50 $\downarrow$	TotalR $\uparrow$
No Adapt.	SAC-Only	1.037	1351	16755 $\pm$ 2042	0.958	2800	15568 $\pm$ 458	1.064	298	24548 $\pm$ 123	1.060	465	24396 $\pm$ 109
Online	SAC + Ours	1.077	601	17219 $\pm$ 1484	1.171	142	18234 $\pm$ 442	1.065	116	25546 $\pm$ 124	1.061	373	25453 $\pm$ 112
	SAC+MRAC	1.073	611	17151 $\pm$ 844	1.071	957	17477 $\pm$ 746	1.062	392	25512 $\pm$ 134	1.096	427	25784 $\pm$ 245
	SAC+RLS	1.061	1051	16968 $\pm$ 1101	1.101	354	17749 $\pm$ 732	1.063	505	25419 $\pm$ 124	1.069	436	25842 $\pm$ 177

Table 2: Cross-platform recovery performance on Agility Cassie (biped) and Unitree H1 (humanoid). Metrics include time-to-recovery at 50% (TTR-50), steady-state ratio (SSR), and total episode return (TotalR

\pm

std over 30 trials). Lower is better for TTR-50; higher is better for SSR and TotalR.

Figure 2: Go1 recovery, empirical boundedness, residual-authority sensitivity, and hardware platforms. (a) Normalized reward after a mid-episode $0.80\times$ actuator-scaling shift. (b) Deviation from the nominal manifold under mild, boundary, and out-of-envelope shifts; in-envelope trajectories remain bounded, while the most severe case fails. (c) Recovery AUC across mass-increase severities and residual bounds; removing the SAG bound degrades performance. Panels (a–c) show Go1 results; (d,e) show the AgileX Scout Mini and Trossen ViperX 300S used for hardware validation.

	Full	No CF	No Dual-Head	No Olivary	No Persistence Gate	No Dir. Align	No Temp. Filt.
TTR-50 $\downarrow$	168	171	186	273	174	3367	1127
AUC $\uparrow$	1.042	1.040	1.039	1.041	1.003	1.021	1.023
SSR $\uparrow$	1.044	1.042	1.005	1.040	1.002	1.018	1.024
TotalR $\uparrow$	20150 $\pm$ 295	20006 $\pm$ 297	19971 $\pm$ 276	20140 $\pm$ 294	20143 $\pm$ 294	19762 $\pm$ 526	19793 $\pm$ 136

Table 3: Go1 ablation under a

1.15\times

mass increase (

30

trials). Lower TTR-50 and higher AUC, SSR, and TotalR are better.

	ViperX Act. Dead zone	ViperX Act. Scaling	Scout Mini Emul. load
TTR-50 Nom. $\downarrow$	$556\pm 299$	$498\pm 244$	1000
TTR-50 Ours $\downarrow$	528 $\pm 292$	401 $\pm 186$	86
SSR Nom. $\uparrow$	0.869 $\pm 0.043$	$0.857\pm 0.055$	$0.970$
SSR Ours $\uparrow$	$0.863\pm 0.045$	0.869 $\pm 0.044$	1.001

Table 4: Physical-robot recovery under representative shifts. ViperX reports mean

\pm

standard deviation over

n=10

trials; Scout Mini reports one proof-of-concept trial.

Figure 3: Cross-platform recovery across increasing dynamics-shift severity. (a–d) Representative perturbations for Go1, Cassie, H1, and Scout. (e–h) Steady-state ratio (SSR; higher is better). (i–l) TTR-50 (lower is better). Results are averaged over 30 trials per condition. The proposed method generally accelerates recovery while preserving near-nominal steady-state performance across robot morphologies and control interfaces.

Authority $\backslash$ Capacity	$\mathbf{C}_{-}$	$\mathbf{C}_{0}$	$\mathbf{C}_{+}$
	$p{=}1000$	$p{=}2500$	$p{=}10000$
Frozen SAC	$\geq 4500$
$\mathrm{A}_{0}$ : Raw	$\geq 4500$	$\geq 4500$	$\geq 4500$
$\mathrm{A}_{1}$ : $+$ Bound	$3751{\pm}485$	$3834{\pm}403$	$777{\pm}388$
$\mathrm{A}_{2}$ : $+$ Direction	$451{\pm}282$	$448{\pm}138$	$489{\pm}173$
$\mathrm{A}_{3}$ : $+$ Perf. reg.	$400{\pm}202$	$409{\pm}397$	$448{\pm}183$

Table 5: Authority–capacity factorial on Go1 under

2.1\times

friction (

30

trials). TTR-50 is mean

\pm

standard deviation in steps (

\downarrow

);

\geq 4500

denotes no threshold crossing within the horizon. Columns vary fixed-feature width

p

; rows add SAG mechanisms.

Robot Policy Adaptation

Robot policy adaptation changes or steers learned robot behaviors to handle new tasks, environments, hardware, and user preferences.

See all 173 papers

Oct 27, 2026

When, Where, and What to Correct: Human-Guided Adaptive Residual Correction for Robot Policies

Imitation policies that reliably execute most of a manipulation trajectory can still fail in localized regions requiring last-mile precision. Updating the full policy or exploring residual actions everywhere treats this local failure as a global learning problem. We introduce Adaptive Residual Correction (ARC), a lightweight post-training module that uses reinforcement learning (RL) to learn a residual correction on top of a frozen policy while using sparse human corrections to structure autonomous exploration. Rather than treating human corrections as imitation targets, ARC uses pre-intervention states to determine 'when' residual control should become active and correction geometry to determine 'where' in residual action space autonomous refinement should explore; task reward determines 'what' residual is ultimately executed. Across three precision-manipulation tasks on a real robot, ARC improves average task success from 33.3% to 75.0%. The human corrections define task-dependent 2-3 dimensional subspaces of the seven-joint residual space that retain 96.0-97.7% of squared correction magnitude. Together, these results show that sparse human corrections can localize and constrain autonomous post-training without requiring the observed correction itself to serve as the final action target.

Anukriti Singh, Maxime Caniot, Pratap Tokekar +1

University of Maryland, College Park College Park, MD · Work done during internship at Enchanted Tools. · Enchanted Tools Paris, France

Robot Policy Adaptation Residual Policy Learning Robotic Manipulation Human-in-the-Loop AI Robot Imitation Learning

Ask PDF

Aug 18, 2026

ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human Feedback

Robotic manipulation policies trained via imitation learning, such as Action Chunking with Transformers (ACT), can achieve strong performance under ideal conditions but often remain sensitive to small execution errors and distribution shifts. Correcting these failures typically requires dataset aggregation and full-policy retraining, which is computationally expensive and unsuitable for real-time deployment. In this work, we propose Online Residual Policy Adaptation (ORPA), a framework that enables immediate, feedback-driven correction of robot actions without modifying the underlying policy parameters. ORPA augments a pretrained control policy with a lightweight, feedback-conditioned module that predicts residual adjustments directly in joint space, allowing the system to adapt its behavior at runtime. We evaluate ORPA on a set of precision-sensitive manipulation tasks using the ALOHA platform, demonstrating improvements in success rate and recovery from small perturbations compared to baseline control policies and rule-based inverse kinematics corrections.

Muhammad A. Muttaqien, Tomohiro Motoda, Ryo Hanai +1

Embodied AI Research Team · National Institute of AIST · Tokyo, Japan

Robotic Control Robot Policy Learning Robot Policy Adaptation Robotic Manipulation Residual Policy Learning

Ask PDF

Aug 25, 2026

CARO: Contact-Agnostic Residual Observation for Zero-Shot Robust Quadruped Locomotion

We propose CARO, a contact-agnostic residual observation framework for policy adaptation. CARO embeds a fixed-base Euler--Lagrange model into the reinforcement learning control loop and constructs a torque-level residual observation without requiring torque sensors, explicit contact estimation, or vision-based measurements of the floating-base position and linear velocity. A disturbance observer extracts a structured signal representing dynamics mismatch, while the policy learns to exploit this feedback for online adaptation. CARO is trained under the same terrain, command, and domain-randomization conditions as the nominal policy, without specialized disturbance curricula or additional adaptation supervision. Nevertheless, it achieves substantially improved zero-shot robustness in simulation and sim-to-real transfer tasks involving out-of-distribution payloads, center-of-mass shifts, terrain geometries, abrupt dynamics changes, and elevated-platform landings.

Zihan Yang, Shixuan Han, Kexin Guo +1

School of Aeronautic Science and Engineering, Beihang University, Beijing 100035, China · School of Automation Science and Electrical Engineering, Beihang University, Beijing 100035, China

Robot Policy Adaptation Quadruped Locomotion RL for Legged Locomotion Robust RL Robot Policy Generalization

Ask PDF

Abstract

Robot Policy Adaptation

Explore similar work

When, Where, and What to Correct: Human-Guided Adaptive Residual Correction for Robot Policies

ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human Feedback

CARO: Contact-Agnostic Residual Observation for Zero-Shot Robust Quadruped Locomotion