VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation

Boyao Han; Chen Shi; Jingjing Qian; ZhuoTan Tian; Li Jiang

cs.CVOct 8, 2026

VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation

Authors: Boyao Han, Chen Shi, Jingjing Qian, ZhuoTan Tian, Li Jiang

Organizations: The Chinese University of Hong Kong, Shenzhen · Shenzhen Loop Area Institute · Harbin Institute of Technology, Shenzhen

Abstract

Vision-Language-Action (VLA) models have emerged as powerful foundations for robotic manipulation, but their reliance on fixed camera configurations during training makes them brittle to changes in camera count or pose during deployment. To overcome these limitations, we propose VersaCamVLA, a camera-configurable framework that decouples camera-set representation from action learning. VersaCamVLA learns a unified scene-token interface that maps an arbitrary, variable set of posed RGB views into fixed-size latent scene tokens. This is achieved via multi-signal target-view prediction and Wrist-Augmented Pose Sampling (WAPS), which leverages natural wrist-camera motion for free pose diversity. At deployment, a lightweight spatial encoder injects these compact scene tokens into a pretrained base VLA as a supplementary visual condition, requiring no explicit 3D sensing or novel-view rendering. Experiments on RoboTwin, LIBERO, and a real-robot platform demonstrate that VersaCamVLA consistently outperforms prior VLA methods and direct multi-view baselines, maintaining robust performance across varying camera counts and unseen camera poses.

Figures & tables

Figure 1: Left: Different manipulation tasks prefer different camera views, making a fixed view setup suboptimal. Right: VersaCamVLA augments a vanilla VLA with a camera-configurable scene-token interface that enables flexible view setup at deployment.

Figure 2: Overview of VersaCamVLA. Stage I: A scene encoder aggregates posed RGB views into fixed-size scene tokens, with a training-only decoder predicting RGB, semantic, and edge signals at target views. Stage II: The decoder is discarded, the scene encoder is frozen, and a jointly-trained spatial encoder compresses the tokens into a supplementary visual condition for a pretrained VLA.

Figure 3: Real-world Manipulation Processes. Representative rollouts of VersaCamVLA on three real-world tasks: PickCube, StackCube, and Insert Test Tube, showing key execution states from the initial scene to task completion.

Task	ACT [ 21 ]		DP [ 48 ]		DP3 [ 15 ]		OpenVLA-OFT [ 3 ]		$\pi_{0.5}$ [ 1 ]		VersaCamVLA
Task	Clean	DR	Clean	DR	Clean	DR	Clean	DR	Clean	DR	Clean	DR
Blocks Ranking RGB	0	0	0	0	2	0	0	0	38	11	67	12
Blocks Ranking Size	3	0	1	0	2	1	7	0	12	4	35	6
Hanging Mug	6	0	19	0	35	1	12	0	4	4	10	4
Move Stapler Pad	0	0	0	0	7	0	0	0	5	7	8	5
Open Laptop	72	1	53	0	77	1	82	0	90	70	96	62

Table 1: Simulation results on RoboTwin 2.0. We report success rates (%) on RoboTwin 2.0. All results are reproduced by us. Bold indicates the best performance in each column.

Method	LIBERO-Spatial	LIBERO-Goal	LIBERO-Object	LIBERO-Long	Average
Diffusion Policy [ 48 ]	78.3	92.5	68.3	50.5	72.4
OpenVLA-OFT [ 3 ]	95.2	94.2	95.2	93.2	94.5
$\pi_{0.5}^{\ast}$ [ 1 ]	98.0	94.6	99.0	91.6	95.8
VersaCamVLA	98.2	95.0	97.8	92.4	95.9

Table 2: Simulation results on LIBERO. We report task success rates (%) on LIBERO. Results marked with ∗ are reproduced by us. Bold indicates the best performance in each column, and underlined indicates the second-best performance.

	RoboTwin 2.0		Real Robot
Method	Seen Pose	Unseen Pose	Seen Pose	Unseen Pose
$\pi_{0.5}$	48.88	32.88	41.67	13.33
VersaCamVLA	53.44	52.63	53.33	58.33

Table 3: Robustness to camera-pose variations. Average success rate (%) on RoboTwin 2.0 Clean and real-robot tasks. Bold indicates the best performance in each column.

	RoboTwin 2.0				Real Robot
Method	3V	4V	5V	6V	3V	4V	5V
$\pi_{0.5}$	35.88	48.88	✘	✘	31.67	41.67	✘
VersaCamVLA	52.56	53.44	53.13	55.63	✘	53.33	65.00

Table 4: Effect of input camera count. Average success rate (%) on RoboTwin 2.0 Clean and real-robot tasks. V denotes views. Bold indicates the best performance in each column.

Table 8

RGB	✓	✓	✓	✓
Edge	✗	✓	✗	✓
Semantic	✗	✗	✓	✓
Average SR	20.94	24.75	25.69	29.50

Table 9: Ablation of supervision signals for scene-token learning. Average success rate (%) on RoboTwin 2.0 DR. Bold indicates the best result.

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 4: Camera-pose perturbations on the RoboTwin 2.0 Stack Blocks Three task. The two rows show two of the training camera views. The first column shows the original, unperturbed camera poses, while the remaining four columns show randomly perturbed camera poses used for robustness evaluation.

Task	$\pi_{0.5}$			VersaCamVLA
Task	Seen	Unseen	$\Delta$	Seen	Unseen	$\Delta$
Blocks Ranking RGB	61	18	$-43$	61	56	$-5$
Blocks Ranking Size	44	6	$-38$	31	39	$+8$
Hanging Mug	14	11	$-3$	6	7	$+1$
Move Stapler Pad	8	4	$-4$	9	9	$0$
Open Laptop	90	82	$-8$	96	92	$-4$

Appendix

Table 10: Per-task camera-pose robustness on RoboTwin 2.0. Success rate (%) at seen and unseen poses under matched four-view inputs.

\Delta

denotes Unseen minus Seen in percentage points. Bold indicates the higher value between methods for each task and metric, including ties.

Method (Setup)	Spatial	Goal	Object	Long	Avg
$\pi_{0}$ (Seen)	94.8	87.0	97.0	83.6	90.6
$\pi_{0.5}$ (Seen)	96.8	88.2	96.6	82.4	91.0
VersaCamVLA (Seen)	98.2	95.0	97.8	91.8	95.7
VersaCamVLA (Unseen)	98.2	96.8	95.8	89.8	95.15

Appendix

Table 11: Camera-pose robustness on LIBERO. Success rate (%) within each official suite under four-view inputs. Seen denotes trained camera poses and Unseen denotes perturbed poses. Bold indicates the highest value in each column, including ties.

Method	Seen Pose	Unseen Pose: $\|\Delta\phi\|$
Method	Seen Pose	$[0^{\circ},30^{\circ}]$	$[30^{\circ},60^{\circ}]$	$[60^{\circ},90^{\circ}]$
$\pi_{0.5}$	48.88	43.38	34.13	30.06
VersaCamVLA	53.44	53.25	52.13	53.38

Appendix

Table 12: Generalization across unseen camera-pose shift magnitudes on RoboTwin 2.0. Average success rate (%) at the seen pose and under perturbations grouped by absolute azimuth offset. Bold indicates the best result in each column.

Extrinsic-noise level	$\sigma_{t}$ (mm)	$\sigma_{r}$ (degrees)	Average SR (%)
Clean	0	0	52.56
Moderate	20	2	52.13
Strong	50	5	50.38

Appendix

Table 13: Robustness to camera extrinsic-calibration noise on RoboTwin 2.0. Average success rate (%) under Gaussian perturbations fixed within each episode. Translation and rotation noise levels are specified by their per-axis standard deviations.

Task	3V	4V	5V	6V
Blocks Ranking RGB	67	61	61	67
Blocks Ranking Size	35	31	39	35
Hanging Mug	10	6	9	3
Move Stapler Pad	8	9	13	4
Open Laptop	96	96	94	96
Open Microwave	51	60	57	67

Appendix

Table 14: Per-task camera-count variation on RoboTwin 2.0 Clean . Success rate (%) for a single VersaCamVLA model evaluated with 3, 4, 5, and 6 views (V). Bold indicates the highest value in each row, including ties.

Task	$\pi_{0.5}$			VersaCamVLA
Task	Seen	Unseen	$\Delta$	Seen	Unseen	$\Delta$
PickCube	70	35	$-35$	85	80	$-5$
StackCube	55	5	$-50$	55	60	$+5$
Insert Test Tube	0	0	$0$	20	35	$+15$
Average	41.67	13.33	$-28.33$	53.33	58.33	$+5.00$

Appendix

Table 15: Per-task camera-pose robustness on the real robot. Success rate (%) under matched four-view inputs.

\Delta

denotes Unseen minus Seen in percentage points. Bold indicates the higher value between methods for each task and metric, including ties.

Task	$\pi_{0.5}$ (3V)	$\pi_{0.5}$ (4V)	VersaCamVLA
Task	$\pi_{0.5}$ (3V)	$\pi_{0.5}$ (4V)	4V	5V
PickCube	50	70	85	85
StackCube	40	55	55	65
Insert Test Tube	5	0	20	45
Average	31.67	41.67	53.33	65.00

Appendix

Table 16: Per-task camera-count variation on the real robot. Success rate (%) for

\pi_{0.5}

trained separately at 3 and 4 views and a single VersaCamVLA model evaluated at 4 and 5 views (V). Bold indicates the highest value in each row, including ties.

Task	48 tokens	192 tokens	432 tokens
Blocks Ranking RGB	55	67	55
Blocks Ranking Size	40	35	32
Hanging Mug	8	3	16
Move Stapler Pad	17	4	13
Open Laptop	89	96	92
Open Microwave	20	67	61

Appendix

Table 17: Per-task ablation of compressed scene-token count. Success rate (%) on RoboTwin 2.0 Clean . Token counts refer to the compressed scene tokens passed to the policy. Bold indicates the highest value in each row, including ties.

Task	Pooling	Conv
Blocks Ranking RGB	61	67
Blocks Ranking Size	26	35
Hanging Mug	11	3
Move Stapler Pad	9	4
Open Laptop	91	96
Open Microwave	52	67

Appendix

Table 18: Per-task ablation of spatial encoder architecture. Success rate (%) on RoboTwin 2.0 Clean with pooling or convolutional compression. Bold indicates the highest value in each row, including ties.

Task	RGB only	Multi-signal
Blocks Ranking RGB	13	14
Blocks Ranking Size	6	9
Hanging Mug	6	11
Move Stapler Pad	3	7
Open Laptop	67	63
Open Microwave	12	54

Appendix

Table 19: Per-task ablation of scene-token supervision. Success rate (%) on RoboTwin 2.0 DR with RGB-only or full multi-signal supervision. Bold indicates the highest value in each row, including ties.

Figure 5: Inference latency with varying camera counts. Measurements use a single NVIDIA 4090 at batch size 1. The red dashed line marks the three-view

\pi_{0.5}

reference. VersaCamVLA incurs a smaller latency increase as additional input views are incorporated.

Figure 6: Multi-signal supervision targets on the real-robot Insert Test Tube task. Rows (top to bottom) show the raw RGB observation, the semantic mask produced by a SAM3 segmenter fine-tuned on our real-robot data, and the Canny edge map. Columns (left to right) span four key task states, from the right arm grasping the test tube to the left arm completing insertion into the rack.

Explore similar work

Oct 8, 2026cs.RO

WARP-VLA: Wrist-Camera Adaptation for View-Robust Policy Execution in Vision-Language-Action Models

Despite recent advances in Vision-Language-Action models (VLAs) for robotic manipulation, their performance remains sensitive to changes in camera configuration. The problem becomes more evident in cross-setup deployment, as reproducing the exact camera pose used for training is nearly impossible. Unlike fixed external views, wrist views are more challenging because the camera moves with the robot, causing even small mounting variations to alter fine-grained geometric cues. To address this, we propose WARP-VLA, a camera-view robust VLA for diverse wrist camera configurations. WARP-VLA adopts a Mixture-of-Experts (MoE) architecture where individual experts learn view-specific feature transformations, and a router combines them based on implicit view information. This allows the policy to be deployed without requiring camera extrinsic parameters as additional input. Through experiments on the LIBERO benchmark, WARP-VLA improves the average success rate of pi-0.5 from 39.2% to 78.3% under wrist-view perturbations. The real-robot experiments further show that the feature-level adaptation learned in simulation successfully transfers to diverse deployment settings. To facilitate reproducibility and future research, we release our wrist viewpoint robustness benchmark and a plug-and-play implementation.

Junmyeong Lee, Dongmin Shin, Min-Gyu Park +3

Yonsei University. · Korea Electronics Technology Institute(KETI).

Robustness of VLA Models Vision-Language-Action Models Test-Time Adaptation of VLA Models Robot Manipulation Benchmarks

Ask PDF

Jul 6, 2026cs.CV

From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model

Real-world robot deployment rarely maintains the training-stage camera setup, where cameras often experience repositioning or remounting depending on actual scenarios. Existing view-robust Vision-Language-Action (VLA) policies tolerate such camera variations only when the camera extrinsics are explicitly provided, making them fragile and hard to use especially when view robustness is critical. We argue that the policy should not be told where the camera is, but rather figure it out by itself. To this end, we introduce Camera-Centric VLA (CamVLA), a new VLA model that decouples manipulation controls from camera geometry by predicting (i) a camera-centric end-effector action expressed in the local camera frame, and (ii) a 6-DoF hand-eye matrix relating cameras to the robot base. A deterministic geometric transformation composes the two predictions into a robot base-frame action. This disentangles how I should move in pose-independent camera-centric action generation from where I am looking from in camera-perspective geometric grounding. The resulting policy is calibration-free, depth-free, and single-view, requiring only a single monocular RGB image as the visual observation and task instruction at deployment. Evaluations in both simulation and real-world robot data show that CamVLA consistently improves success rates across diverse unseen viewpoints. Project page: https://alibaba-damo-academy.github.io/CamVLA/.

Wenhao Li, Xueying Jiang, Quanhao Qian +4

1Nanyang Technological University · 2DAMO Academy, Alibaba Group · 3HuPan Lab +1

Language-Conditioned Robot Manipulation Hand-Eye Calibration Vision-Language-Action Models Vision-Based Robot Control Robustness of VLA Models

Ask PDF

Jun 23, 2026cs.RO

G $^3$ VLA: Geometric inductive bias for Vision-Language-Action Models

Vision-language-action (VLA) models have made rapid progress in generalist robot manipulation by harnessing semantic knowledge from pretrained vision-language backbones, but their visual tokens remain grounded in 2D image coordinates rather than the calibrated geometry of the robot's cameras -- a mismatch especially pronounced in multi-camera setups, where views are coupled by known intrinsics and extrinsics yet processed as independent images. We propose G

^3

VLA, a camera-aware geometric module that injects calibrated structure into the visual-token stream of a pretrained VLA without altering its action space or imitation objective, combining intrinsic-conditioned ray embeddings, projective positional encoding (PRoPE), and bidirectional cross-view fusion. Geometric supervision is provided either from ground-truth point maps when available, or from confidence-gated

π^3

X teacher predictions, requiring no depth sensors or manual annotations. Instantiated on

π_0

, G

^3

VLA yields consistent gains across the LIBERO suites, RoboCasa24, RoboTwin2.0, and real-robot settings, with the largest improvements on spatially and object-sensitive tasks. We further validate on

π_{0.5}

and GR00T 1.5, with results suggesting that geometric transfer is most effective when geometry-aware tokens have direct access to the action generation pathway. Our project page is at https://sites.google.com/view/g3vla

Yue Peng, Yongzhe Zhao, Artur Habuda +5

New York University Shanghai · Technical University of Denmark · MBZUAI - Mohamed bin Zayed University of Artificial Intelligence

Multi-View Learning Robotic Manipulation Vision-Language-Action Models

Ask PDF

Abstract

Explore similar work

WARP-VLA: Wrist-Camera Adaptation for View-Robust Policy Execution in Vision-Language-Action Models

From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model

G3^33VLA: Geometric inductive bias for Vision-Language-Action Models

G $^3$ VLA: Geometric inductive bias for Vision-Language-Action Models