← Paper Digest

DAPPT: Domain-Aware Policies from Procedural Trajectories for Sim-to-Real Dexterous Tool Use

Beining Han, Jia Deng

November 2026

TL;DR Train a dexterous hand-arm policy in rigid-body-only simulation to track procedurally generated tool trajectories, with the trajectory parameters as a policy input that can be tuned per task. Picking the best parameters raises task metrics 1.5-3.8x in a particle simulator, and the policy transfers zero-shot to a real robot on six tasks such as sand scooping and play-dough rolling.

What they do

Tool use with sand, dough or liquids is slow to simulate and hard to transfer, which rules out large-scale RL. DAPPT never simulates the non-rigid material. It simulates only the rigid tool and trains a policy to track procedurally generated tool trajectories, such as a scoop entering sand at a given angle, depth and speed. The trajectory parameters (“domain parameters”) are a policy input, so at test time one can search for the setting that gives the best task result.

How it works

  • Procedural trajectories. Each task defines a parameterized 6D pose or joint trajectory of the tool, plus a contact trajectory saying which hand links touch the tool and where.
  • Teacher. PPO in IsaacLab trains a state-based policy for a Franka Research 3 arm with a 12-DoF XHand1 hand, with randomized domain parameters, contact and pose-tracking rewards, a decaying behavior-cloning term from 10-20 simulated demos, and domain randomization. Arm damping gains are calibrated to real open-loop trajectories.
  • Student. DAgger distills the teacher into a PointNet++ point-cloud policy that also takes the domain parameters.
  • Parameter selection. Random search in Genesis, which simulates sand and dough with MPM, picks the best parameters per task.

Results

  • Best vs. average parameters improves task metrics 1.5-3.8x in Genesis (scooped sand: 3.64 g to 13.9 g).
  • DAPPT beats SimToolReal on all six tasks; that baseline, even with ground-truth object poses, scores near zero on scraping, rod-rolling, dispenser and spray.
  • Training only on the best parameters instead of all domains drops the task metric 49-98% on the three tasks tested.
  • Real robot, zero-shot, 20 trials per task: task success 14/20 scooping, 11/20 rod-rolling, 19/20 scraping, 19/20 mouse-wheel, 14/20 dispenser, 10/20 spray (no water emitted). Real scooping gets 7.7 g with the best parameters vs 2.9 g with mean parameters.

Limitations

Policies generalize only to a narrow range of object poses and assume a known object. Domain parameters and trajectory functions are hand-designed for each task.

Figures

From Figure 1: Six real-world tasks on the 19-DoF hand-arm system, learned in rigid-body simulation and transferred z...
From Figure 1: Six real-world tasks on the 19-DoF hand-arm system, learned in rigid-body simulation and transferred zero-shot. Left: scraping sand, rod-rolling play-dough, scooping sand. Right: mouse-wheel scrolling, dispenser pressing, spray triggering.
From Figure 2: The domain-aware policy takes proprioception, a point cloud and domain parameters. For sand scooping, ...
From Figure 2: The domain-aware policy takes proprioception, a point cloud and domain parameters. For sand scooping, the parameters are the insertion angle, insertion distance, and insertion and lifting speeds of the scoop trajectory.
From Figure 3: Percentage difference of the best domain parameters over the average ones in the Genesis particle simu...
From Figure 3: Percentage difference of the best domain parameters over the average ones in the Genesis particle simulator, for task metric and per-step tracking error.
From Figure 5: Real rollouts with the best domain parameters (top) versus other parameters (bottom) for scooping, scr...
From Figure 5: Real rollouts with the best domain parameters (top) versus other parameters (bottom) for scooping, scraping and rod-rolling.
Abstract

Sim-to-real RL has achieved impressive results in dexterous manipulation but remains limited to tasks with accurate rigid-body simulation. However, these methods cannot be applied to skills that involve deformable and particles, with which the simulation speed will become too slow for large-scale RL learning. We present DAPPT, a sim-to-real framework for end-to-end dexterous tool-use manipulation skills, e.g., sand scooping, play-dough rod-rolling, without simulating non-rigid materials. Our method learns a domain-aware RL policy by tracking procedural trajectories parameterized by domain parameters, and distills it into an end-to-end domain-aware sensorimotor policy. Furthermore, explicit domain represen-tation enables fast selection of domain parameters that can maximize downstream task performance. We evaluate DAPPT end-to-end on six dexterous manipulation tasks, including sand scooping, play-dough rod-rolling, sand scraping, mouse-wheel scrolling, dispenser pressing, and spray triggering. Our method achieves 1.5-3.8x in task metrics through the best domain parameter and transfers zero-shot to the real world.

Summaries are written automatically from each paper's text. Figures and videos come from the paper and its project page; all credit goes to the authors.