- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
WDRS is a training-free site adaptation method: it reuses the intermediate state of a successful trajectory from the frozen flow strategy, re-solves the sampled trajectory under the current observation, uses density gating to determine when to hand over control, and fits the motion space constant offset with the success label to correct the fixed spatial offset of the deployment station.
Critical strengths
Overall, the paper is clearly motivated and well structured. The writing is clear, and the authors provide thorough experimental analyses to support and validate the proposed approach.
Critical weaknesses
-
The method only works for small-to-moderate jitter on a fixed site. Layouts that change across deployments, large non-persistent shifts, and multiple heterogeneous sites are not covered.
-
The frozen policy must succeed at least once at the site. If it never does, the method cannot start, and boarding can be expensive when success is rare.
-
The paper gives default values for the gate threshold, warm-up length, and CEM settings, but there is little evidence that these hold across backbones and tasks.
-
The paper does not give matched-compute comparisons of wall-clock time, memory, or total inference cost against the frozen policy and training-free baselines.
-
Only simulated benchmarks are used, with no real-robot validation.
Questions for authors
Please see the weaknesses.
5 comments
W5
Thanks for the comments. To validate the practicality of our method on a physical robot, we deployed the full framework on a Franka Panda. Following the DROID platform, we use two cameras (wrist and external). Our base model is π0.5-DROID, which we fine-tuned to calibrate for our camera viewpoints and gripper. We will release all hardware components, model configurations, and checkpoints with the paper. We evaluate on two tasks: (1)“pick up the banana and put it into the bowl” and (2)“pick up the black cube and put it on the white paper.” We ran 4 experimental groups, each with a different angular perturbation, and evaluated each group over 16 trials. The results are as follows:
| Method | #1 | #2 | #3 | #4 | Total |
|---|---|---|---|---|---|
| Frozen Policy | 5/16 | 7/16 | 5/16 | 8/16 | 25/64 = 0.391 |
| Open-loop Replay | 2/16 | 3/16 | 1/16 | 3/16 | 9/64 = 0.140 |
| Ws | 7/16 | 8/16 | 8/16 | 6/16 | 29/64 = 0.453 |
| Ws+Dg | 7/16 | 8/16 | 9/16 | 7/16 | 31/64 = 0.484 |
| RS | 9/16 | 10/16 | 8/16 | 8/16 | 35/64 = 0.547 |
| WDRS | 11/16 | 8/16 | 10/16 | 11/16 | 40/64 = 0.625 |
WDRS improves the success rate by about 23.4% over the frozen policy, consistent with our findings in simulation. We also observe that the gain from replay is smaller than in simulation. This is because the real-world policy experiences more disturbances, and outcomes are more sensitive to collisions than in simulation. We are working on continually evaluating more tasks to further validate the practicality of the method.
We further evaluated two additional physical robot tasks: “pick up the bottle and put it on the white paper” and “pick up the cube or banana and put it into the bowl.” The frozen policy starts from a higher initial SR on these two tasks, and WDRS constantly improves the success rate by about 31%, bringing it close to 100%, as shown following:
| Method | #1 | #2 | #3 | #4 | Total |
|---|---|---|---|---|---|
| Frozen Policy | 12/16 | 10/16 | 10/16 | 11/16 | 43/64 = 0.672 |
| Open-loop Replay | 11/16 | 12/16 | 1/16 | 10/16 | 34/64 = 0.531 |
| Ws | 14/16 | 16/16 | 11/16 | 10/16 | 51/64 = 0.797 |
| Ws+Dg | 14/16 | 16/16 | 12/16 | 10/16 | 52/64 = 0.812 |
| RS | 16/16 | 14/16 | 13/16 | 15/16 | 58/64 = 0.906 |
| WDRS | 15/16 | 16/16 | 16/16 | 16/16 | 63/64 = 0.984 |
W1
We thank the reviewer for the detailed suggestion. We think that in practical deployment, large shifts that are random and non-persistent are rare. For example, in a household, the positions of the microwave or a bowl do not change drastically from one episode to the next, but small displacements are present every time. Moreover, a fully random large shift is inherently hard to adapt to at deployment time without demonstrations, unless the base policy is already sufficiently robust or an additional strongly generalizing supervision module is introduced. We therefore decompose such shifts into small-scale shifts and address them within that small range. This is the point Figure 1 is meant to illustrate.
The case of multiple large shifts (i.e., multiple sites) can be handled by adding a retrieval layer on top of our method, as discussed in RTS (retrieve-and-steering). The matching WDRS memory (tape and offset) is retrieved by similarity, so each site reuses its own adapted solution. We will add this discussion as an extension of WDRS in the paper.
W2
As the reviewer notes that the method needs a success before it can be activated, this is precisely the question we set out to answer: what can occasional successes bring to a deployed policy?
We do not aim to improve generalization or robustness through data augmentation or through repeated interaction during pre-training or post-training. Instead, we consider a trained policy that is deployed on a fixed layout subject to an unknown spatial shift. Our method is a plug-in: it uses no demonstrations and performs no weight updates. Without it, the policy simply runs exactly as deployed.
Nearly all of our baselines, including fine-tuning, RL, and steering, also require successful trajectories to work. This is a basic requirement for this class of methods, not one specific to ours. Our method needs fewer successes than these baselines. Ws needs only a single successful trajectory. RS does not even require a tape: it needs only one perturbed attempt during its search to succeed, so it can bootstrap from a near-zero SR. For example, on one GR00T site the frozen policy succeeds in 0/15 trials, while RS alone reaches 10/15. By contrast, fine-tuning-based methods require considerably more successful trajectories. Table 1 compares the sample efficiency of all methods under the same budget.
When the policy never succeeds at a site, Ws and Dg are never invoked, and the policy runs natively. In this case, only demonstration-based approaches (e.g., in-context methods) can work efficiently without extra exploration. In practice, however, collecting demonstrations for every possible spatial shift is infeasible. We consider this case outside the scope of our work. It calls for a better base model or additional training data.
W3
Apart from the integration start t0, every hyperparameter was held fixed across all three backbones (π0.5, GR00T N1.7, πRL), both LIBERO suites, all three jitter levels and LIBERO-plus: the gate quantile q=0.08, the warm-up (10 attempts, pool of at least 40 chunks), the density estimator (50 reverse steps, 2 reference samples, 1 probe) and the CEM settings (4×15 attempts, s0=0.02, smin=0.006, shrink 0.85, clip 0.06). Only t0 was recalibrated per backbone because the backbones use different numbers of integration steps (§4).
We parameterise the gate by a within-site quantile rather than an absolute log-density, precisely because absolute values do not transfer: the median threshold is −435, −458 and −48 nats on the three backbones. A quantile is invariant to these offsets, and the realised firing rate tracks q.
W4
We thank the reviewer for the suggestion. We have compared the computational efficiency and memory footprint of all baselines, with all models run in FP32. The results are shown in the table below:
Our method stores only a small amount of intermediate state, so it adds roughly 500 MB of memory. WDRS computes a density gate to decide when to hand over, which requires two additional reverse ODE integrations. As a result, its end-to-end latency is about 2.2× that of the frozen policy.
The 2.2× overhead applies only while the method is still optimizing. Once optimization is complete, the tape is fixed, and the offset has been estimated, so the density gate can be replaced by a constant gate. Inference latency then returns to the same level as the frozen policy.