Evolving Dexterous Robots from Scratch

Zihan Guo; Shuzhe Zhang; Muhan Li; Peiyang Li; Sam Kriegman

cs.ROSep 27, 2026

Evolving Dexterous Robots from Scratch

Authors: Zihan Guo, Shuzhe Zhang, Muhan Li, Peiyang Li, Sam Kriegman

Organizations: Northwestern University

Abstract

Little is known about how to manually design agents capable of dexterous manipulation. Some design principles have been inferred from close examination of how animals manipulate objects, but these structures and behaviors have so far resisted biomimicry and may not be optimal for artificial machines. Here we evolve freeform robots to pick up, hold, rotate, and use diverse objects. Unlike other approaches to optimizing robot hands, we do not presuppose the presence, articulation, or geometry of any part of the body. Although familiar prehensile forms such as tails, beaks, paws and claws may emerge spontaneously under certain conditions--and while such conditions could be of interest to evolutionary biologists--de novo manipulator design can also reveal whole new solutions, overlooked or unknown structures which may be better suited for the task at hand. We use contrastive learning to create a highly searchable genetic embedding of design space, an autoregressive developmental model to decode designs, evolutionary strategies to find good designs, and reinforcement learning to train each evolved design. Winning designs were automatically converted into a manufacturable blueprint, printed, assembled and tested in the real world in a zero-shot manner. The results represent the state-of-the-art in evolutionary robotics in terms of performance, diversity and complexity.

Figures & tables

Figure 1: Evolving freeform manipulators. Under different selection pressures and environmental conditions, unique morphologies emerged to rotate ( A-D ), retrieve ( E-H ), flip ( I-K ), hold ( L-N ), pick up ( O-R ), and hang from ( S-V ) objects. Evolution operates in a latent space (multicolored surface, center inset) of genotypes, which are visualized as colored barcodes below each decoded design (A,G,I,M,O,U). The resulting robot was trained in simulation (D,H,K,N,R,V), and in some cases built and tested in the real world (C,E,Q,S).

Figure 2: Latent genome and developmental decoder. Morphologies were embedded on a latent manifold ( A ) and autoregressively decoded back to morphospace ( B ) through a developmental program ( C-G ) that translates design tokens ( H ) into articulated bodies ( I-L ). Dimensions of an evolved genotype (barcodes in C-G) most strongly correlated with each design token are highlighted in the corresponding color at each growth step. The decoder outputs a probability distribution (vertical histogram in C) for each token that determines how new structures are layered on top of earlier structures, and their 3D geometry (E,F) and articulation (D,G).

Figure 3: Genetic interpolation between four evolved manipulators. Spherical linear interpolation (slerp) between a retriever (top left), a rotator (top right), a picker (bottom right), and a hanger (bottom left). The latent genotype, $z_{i}\in\mathbb{S}^{31}$ , below each decoded design is visualized as a double barcode. The upper and lower rows of the barcode show the positive and negative component of each latent dimension, respectively, with darker colors indicating greater magnitude.

Figure 4: Two evolved rotators. In our main experiment, robots were evolved to rotate diverse objects. The best was essentially didactyl ( A-E ). It possessed two functional appendages and a third, very short vestigial appendage that did not contribute to object rotation. Another highly fit evolved design which we built was tetradactyl ( F-J ); all four of its appendages were utilized.

Figure 5: An evolved picker, hanger, and retriever. We evolved, trained, and realized robots that pick objects off a surface ( A-D ), hang from a horizontal bar with a weight suspended below them ( E-H ), and retrieve objects from within a narrow pipe ( I-K ).

Figure 6: An evolved multitasker. We also evolved a generalist to carry out several tasks. The winning design ( A,B ) could rotate ( C ), flip ( D ), pick up ( E ), and hang ( F ) from objects in simulation.

Figure 7: The evolution of rotators (fitness measured during evolution; results after finetuning are in Sect. 3.2 ). Our approach consistently yields novel robots that rotate objects faster than those produced by related prior work, where our full model was trained with the 2 million sample dataset ( A ) and the proposed genetic representation increased evolvability beyond what could be achieved with a VAE, both trained in the smaller 200,000 sample dataset ( B ). In the full setting, morphologies evolved that made learning much easier ( C ). Shaded regions indicate standard error of the mean. Here results are reported before policy distillation and finetuning.

Appendix figures & tables32 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 8: One design. The root is the central body: the hub at its centre and five spokes around it. Three spokes are active and so built, each ending at the tip from which an appendage grows; two are inactive and not built. A web fills the space between neighbouring built spokes. Each appendage is a chain of segments, and each joint between two segments is marked by the hinge axis it takes, lateral or normal. Segments are drawn slightly apart so that every joint shows. The parameters of the root and of an appendage are shown one by one in Figs. 9 and 10 .

Parameter	Range	Bins	Parameter	Range	Bins
Root hub			Appendage joint
root hub aspect	0.8 to 3.0	12	appendage joint yaw bend	$-0.24$ to $0.24$ rad	32
root hub ring fraction	0.5 to 1.0	12	appendage joint hinge axis	lateral or normal	2
root hub radius	0.02 to 0.05 m	12	appendage joint pitch bend	$-0.26$ to $0.26$ rad	32
root hub infill	1.0 to 4.0	8	appendage joint length	0.03 to 0.06 m	32
Root spoke and web			Appendage segment

Appendix

Table 1: Design-space parameters. The root is described by 39 values and each segment of an appendage, with its joint, by 12. Rows follow the panels of Figs. 9 and 10 . Bins is the number of bins used to write the parameter as a token (Appx. B.3 ).

Figure 9: The root. Top: one root from the design space, seen from above (left), from the end (right) and from the side (bottom). The purple ellipse is the hub. An orange bar with an arrow marks the tip of each spoke that is built. A–K : one parameter each, cut and enlarged from the views above; the small circle on the views marks where each was cut. Root hub: A Root hub aspect , B Root hub ring fraction , C Root hub radius , D Root hub infill . Root spoke and web: E Root spoke azimuth , F Root spoke activation , G Root spoke elevation , H Root spoke radius , I Root spoke length , J Root web radius , K Root web reach .

Figure 10: The appendage. Top: one appendage of the same root, growing from its spoke tip at the left; each segment is drawn as a chain of beads around its outline. A–L : one parameter each, cut and enlarged from the appendage above; the small circle marks where each was cut. Appendage joint: A Appendage joint yaw bend , B Appendage joint hinge axis , C Appendage joint pitch bend , D Appendage joint length . Appendage segment: E Appendage segment asymmetry , F Appendage segment gain , G Appendage segment lobe , H Appendage segment phase , I Appendage segment width , J Appendage segment depth , K Appendage segment taper , L Appendage segment twist .

Figure 11: Sensitivity analysis of the design variables. We measured how much each variable of the design changes the body. Across 1,000 designs, each variable in turn was changed by a random amount (10% of its range on average) and the body was voxelized before and after the change. The change of the body is one minus the intersection over union (IoU).

Figure 12: Data augmentation. Two designs and the operations used to create their positive pairs. The original design is shown in gray behind each augmented copy.

Symbol	Meaning
$\mathbf{p}$ , $\mathbf{p}_{0}$	position of the object, and its start position
$\mathbf{p}^{\ast}$	point under the root at which the object is held
$r$	distance of the object from its start position along the table, $\|\mathbf{p}_{xy}-\mathbf{p}_{0,xy}\|$
$h$	height of the object above its start position
$\theta$	angle between the orientation of the object and the goal orientation
$\omega$	rotation rate of the object about the task axis

Appendix

Table 2: Symbols used in the reward tables.

	Wooden Cube (134.5 g)		Rubber Cube (26.8 g)		Rubik’s Cube 3x (92.9 g)		Rubik’s Cube 4x (132.3 g)		Fabric Cube (16.1 g)
Design	$\omega$	$T$	$\omega$	$T$	$\omega$	$T$	$\omega$	$T$	$\omega$	$T$
LEAP (Multi-obj)	—		—		—		—		—
LEAP (Cube-only)	$\text{1.7}_{\scriptscriptstyle\pm\text{0.1}}$	$\text{20.0}_{\scriptscriptstyle\pm\text{7.0}}$	$\text{0.2}_{\scriptscriptstyle\pm\text{0.0}}$	$\text{30.0}_{\scriptscriptstyle\pm\text{0.0}}$	$\text{0.3}_{\scriptscriptstyle\pm\text{0.0}}$	$\text{30.0}_{\scriptscriptstyle\pm\text{0.0}}$	$\text{0.3}_{\scriptscriptstyle\pm\text{0.0}}$	$\text{30.0}_{\scriptscriptstyle\pm\text{0.0}}$	—
Ours (Tetradactyl)	$\text{{1.8}}_{\scriptscriptstyle\bm{\pm}\text{{0.1}}}$	$\text{{30.0}}_{\scriptscriptstyle\bm{\pm}\text{{0.0}}}$	$\text{1.9}_{\scriptscriptstyle\pm\text{0.0}}$	$\text{30.0}_{\scriptscriptstyle\pm\text{0.0}}$	$\text{1.7}_{\scriptscriptstyle\pm\text{0.1}}$	$\text{30.0}_{\scriptscriptstyle\pm\text{0.0}}$	$\text{1.8}_{\scriptscriptstyle\pm\text{0.3}}$	$\text{21.3}_{\scriptscriptstyle\pm\text{7.0}}$	$\text{{1.7}}_{\scriptscriptstyle\bm{\pm}\text{{0.1}}}$	$\text{{30.0}}_{\scriptscriptstyle\bm{\pm}\text{{0.0}}}$
Ours (Didactyl)	$\text{1.5}_{\scriptscriptstyle\pm\text{0.3}}$	$\text{30.0}_{\scriptscriptstyle\pm\text{0.0}}$	$\text{{2.4}}_{\scriptscriptstyle\bm{\pm}\text{{0.5}}}$	$\text{{30.0}}_{\scriptscriptstyle\bm{\pm}\text{{0.0}}}$	$\text{{2.0}}_{\scriptscriptstyle\bm{\pm}\text{{0.0}}}$	$\text{{30.0}}_{\scriptscriptstyle\bm{\pm}\text{{0.0}}}$	$\text{{1.9}}_{\scriptscriptstyle\bm{\pm}\text{{0.2}}}$	$\text{{30.0}}_{\scriptscriptstyle\bm{\pm}\text{{0.0}}}$	$\text{1.4}_{\scriptscriptstyle\pm\text{0.2}}$	$\text{30.0}_{\scriptscriptstyle\pm\text{0.0}}$
	Tomato Soup Can (353.2 g)		Moon Ball (30.9 g)		Apple (364.6 g)		Orange (212.6 g)		Avocado (223.8 g)

Appendix

Table 3: Real-world in-hand rotation performance across diverse unseen objects. We report the mean rotation speed (

\omega

, rad/s) and stable rotation time (

T

, s), with sample standard deviations shown as subscripts. Rotation speeds are evaluated in two trials. Stable rotation time is evaluated in three 30 s trials. For each object, both metrics are bolded for the design with the highest mean rotation speed, determined before rounding. An em dash indicates failure to sustain in-hand rotation.

Term	Equation	Weight
rotation toward goal	$1/(\|\theta\|+0.1)$	$1$
goal reached	$\|\theta\|\leq 0.2$	$250$
steady rotation	$0.25<\omega_{z}<1.5$	$1$
object displacement	$\|\mathbf{p}-\mathbf{p}_{0}\|$	$-10$
object drift	$\max(\|\mathbf{p}-\mathbf{p}_{0}\|-0.03,\,0)$	$-0.1$
action magnitude	$\|\mathbf{a}_{t}\|^{2}$	$-2\mathrm{e}{-4}$

Appendix

Table 4: Reward terms of the rotate task.

Term	Equation	Weight
approach	$\mathrm{mean}_{i}\,\exp(-d_{i}/0.02)$ , before first contact	$0.4$
contact	$\mathrm{mean}_{i}\,f_{i}$	$0.8$
multiple contacts	at least two appendages touch the object	$0.8$
lift	$\mathrm{clip}\big((h-0.022)/0.008,\,0,\,1\big)$	$8$
near the root	$\exp(-\|\mathbf{p}-\mathbf{p}^{\ast}\|/0.05)$	$2$
stable grasp	held, at least two contacts, and nearly at rest	$2$

Appendix

Table 5: Reward terms of the pick task.

Wooden Cube	Rubber Cube	Rubik’s Cube 3x	Rubik’s Cube 4x	Fabric Cube	Cube Toy	Lemonade Mix Box	Tennis Ball	Moon Ball	Orange	Avocado	Donut Toy
10/10	10/10	8/10	8/10	10/10	7/10	10/10	6/10	5/10	9/10	5/10	4/10
Water Can	Candle Jar	Pudding	Polygon Toy	Jam Jar	Energy Stick	Meat Can	Toy Bear	Disney Toy	Baby Bottle	Motor	Salt Container
10/10	6/10	10/10	8/10	6/10	10/10	10/10	10/10	10/10	10/10	10/10	0/10

Appendix

Table 6: Real-world performance on the pick task across diverse objects. Results indicate successful picks out of 10 trials per object.

Term	Equation	Weight
approach	$\mathrm{mean}_{i}\,\exp(-d_{i}/0.02)$ , before first contact	$0.4$
contact	$\mathrm{mean}_{i}\,f_{i}$	$0.8$
multiple contacts	at least two appendages touch the bar	$0.8$
stability †	$\mathrm{mean}_{i}\,f_{i}\cdot\exp(-s/0.0075)$ , if at least two contacts	$8$
stable grasp †	at least two contacts and $s\leq 0.0075$	$2$
joint torques	$\|\bm{\tau}\|^{2}/\tau_{\mathrm{ref}}$	$-0.5$

Appendix

Table 7: Reward terms of the hang task. Terms marked with

\dagger

are active only after release.

\tau_{\mathrm{ref}}

is a hyperparameter.

Term	Equation	Weight
new progress	$\min(\Delta g^{\star},\,0.1)$	$40$
new progress in contact	$\min(\Delta g^{\star},\,0.1)$	$40$
new progress, unclipped	$\Delta g^{\star}$	$80$
new progress, squared	$\Delta(g^{\star})^{2}$	$80$
net progress	$\mathrm{clip}(\Delta g,\,\pm 0.1)$	$10$
proximity	$\mathrm{clip}(\Delta p,\,\pm 0.25)$	$5$

Appendix

Table 8: Reward terms of the retrieve task.

Term	Equation	Weight
Flip stage
progress toward goal	$\max(-\Delta\theta,\,0)$	$10$
goal reached	$\theta\leq 0.1$	$250$
steady rolling	$0.25<\omega<1.5$	$1$
rolling backward	$\max(-\omega,\,0)$	$-1$
Return stage

Appendix

Table 9: Reward terms of the flip task.

Term	Equation	Weight
grasp progress	$G_{t}-G_{t-1}$ , before release	$0.5$
contact †	$\mathrm{mean}_{i}\,f_{i}$	$0.25$
multiple contacts †	at least two appendages touch the handle	$0.25$
hold ‡	$1$	$1$
no slip ‡	$1/(1+S)$	$8$
action smoothing	$\|\mathbf{a}_{t}-\mathbf{a}_{t-1}\|^{2}$	$-0.005$

Appendix

Table 10: Reward terms of the hold task. The grasp score is

G=0.2\,\mathrm{mean}_{i}\,e^{-d_{i}/0.02}+0.4\,\mathrm{mean}_{i}\,f_{i}+0.4

, and the slip cost is

S=0.25\,(s_{\mathrm{a}}/0.02)^{2}+0.25\,(s_{\mathrm{l}}/0.015)^{2}+0.5\,(s_{\mathrm{r}}/0.35)^{2}

, where

s_{\mathrm{a}}

s_{\mathrm{l}}

and

s_{\mathrm{r}}

are the slip along, across, and about the handle. Terms marked with

\dagger

are active only after release; those marked with

\ddagger

are, in addition, multiplied by

\mathrm{mean}_{i}\,f_{i}

when at least two appendages touch the handle, and by 0 otherwise.

Figure 14: The evolution of multitaskers. Robots were evolved to rotate, flip, pick, hold, and hang. Unified fitness (A) was the sum of task normalized scores. The task scores of the best design found so far (B-F) reveal trade-offs: gains in unified fitness did not always improve performance on every task. Selected designs (G-M) correspond to the labeled points in A.

Figure 15: Real-world in-hand rotation across diverse objects for didactyl design.

Figure 16: Real-world in-hand rotation across diverse objects for didactyl design.

Figure 17: Real-world in-hand rotation across diverse objects for tetradactyl design.

Figure 18: Real-world picking across diverse objects using the four-appendage design.

Figure 19: Real-world picking across diverse objects using the four-appendage design.

Figure 20: Real-world test objects. The everyday objects used in the real-world rotate and pick experiments: rigid and soft, smooth and textured, from a 16 g fabric cube to a 687 g salt container.

Figure 21: The five physical designs. From left to right: the retriever (purple), the didactyl rotator (grey), the picker (white), the 4-appendage rotator (grey) and the hanger (tan). Each is 3D-printed in PLA with one actuator per joint; parts are listed in Table 17 . Their real-world results are in Tables 3 and 6 and Figs. 4 – 5 .

Model	Validity			Smoothness
Model	App. acc.	Joint acc.	Valid	Recall@1	Edit $\rho$	Topology 10-NN acc.	Length 10-NN $r$	Volume 10-NN $r$
Ours (2M)	1.00	0.96	0.82	1.00	$0.97\pm 0.10$	0.92	0.97	0.91
Ours (200k)	1.00	0.84	0.65	1.00	$0.99\pm 0.05$	0.76	0.96	0.90
w/o $z\in\mathbb{S}^{31}$	1.00	0.80	0.64	1.00	$0.99\pm 0.05$	0.71	0.95	0.88
w/o $\mathcal{L}_{\mathrm{con}}$	1.00	0.95	0.67	0.03	$0.97\pm 0.09$	0.59	0.82	0.73
VAE	0.44	0.06	0.33	0.01	$0.93\pm 0.13$	0.02	0.79	0.79

Appendix

Table 11: Ablation of the latent genome. All validity metrics, Recall@1, and Edit

\rho

use the 2,000-design test set; all three 10-NN metrics use a separate set of 4,500 designs. The best and second best values in each column are shaded.

Figure 22: Genetic coherence. Ten thousand unique, pentadactyl morphologies were generated, copied, and the copy was rotated by a randomly selected angle. The resulting design pairs are visualized by UMAP ( Healy and McInnes, 2024 ) along 2D projections of four different latent embeddings ( A-D ). A gray line connects the original (filled circle) to its rotated (open circle) counterpart. Five design variants were considered for this analysis, those with a pair of three-jointed appendages and three two-jointed appendages (3,3,2,2,2), four three-jointed and one two-jointed (3,3,3,3,2), one four-jointed and four three-jointed (4,3,3,3,3), three four-jointed and two three-jointed (4,4,4,3,3), and five four-jointed appendages (4,4,4,4,4). In the VAE, rotated copies can appear far from their originals in the UMAP projection (D). With the contrastive loss, rotated copies remain close to their originals in the UMAP projection (A–B); without it, the two views separate (C). Removing the spherical projection, $z\in\mathbb{S}^{31}$ , had little effect on this pairing (B).

Layer	Description
Voxel input	$128^{3}\times 2$
Stem	Conv, kernel size $3^{3}$ , stride 2, to $64^{3}$ , 32 channels, batch normalization, ReLU
Stage 1	2 $\times$ ResBlock, downsample to $32^{3}$ , 64 channels
Stage 2	2 $\times$ ResBlock, downsample to $16^{3}$ , 128 channels
Stage 3	2 $\times$ ResBlock, downsample to $8^{3}$ , 256 channels
Stage 4	2 $\times$ ResBlock, downsample to $4^{3}$ , 512 channels

Appendix

Table 12: Encoder architecture.

Layer	Description
Input	$z\in S^{31}$ , and the tokens predicted so far
Memory	Linear in: 32, out: $8\times 384$ (eight vectors)
Embedding	token embedding (137) + learned position embedding (368), 384 channels
Layers 1–4	Transformer decoder layer: causal self-attention, attention to the eight vectors, feed-forward (1536, GELU); 8 heads, layer normalization before each part
Head	Linear in: 384, out: 137
Output	logits of the next token: 137

Appendix

Table 13: Decoder architecture.

Parameter	Value
CMA-ES
Population size	32
Initial step size ( $\sigma_{0}$ )	0.25
Fitness of Rejected Designs
Failed to compile	$-1000$
Motors do not fit	$-950$

Appendix

Table 14: CMA-ES hyperparameters.

Parameter	Range
Observation
Joint position noise (per step)	0 to 0.02 rad
Joint position offset (per episode)	$\pm$ 0.005 rad
Action
Action noise (per step)	0.05 to 0.1
Action delay	0 to 2 control steps

Appendix

Table 15: Domain randomization used for fine-tuning.

Parameter	Value
Parallel environments	4096
PPO iterations	500 for rotate and flip, 200 otherwise
Steps per iteration	32
Policy and value network	GRU (256) + MLP (512, 256, 128), ELU
Learning rate	$5\times 10^{-4}$ ( $3\times 10^{-4}$ ), adaptive
Target KL divergence	0.02

Appendix

Table 16: Reinforcement learning hyperparameters.

Item	Cost (US)	Rotate	Rotate-4	Pick	Hang	Retrieve
XL330-M288-T Actuator	$27.49	15	15	10	10	9
FPX330-H101 Hinge Frame with Idler a	$2.82	15	15	10	10	9
FPX330-S102 Base Frame (Radial) a	$2.50	7	7	10	5	1
FPX330-S101 Side Frame (Lateral) a	$2.50	8	8	0	5	8
Robot Cable-X3P 180 mm b	incl.	15	15	10	10	9
U2D2 USB Converter	$36.92	1	1	1	1	1

Appendix

Table 17: Bill-of-materials (BOM) of the five physical designs. All designs share the same parts: the base and every segment are 3D-printed in PLA, and each actuated joint is one DYNAMIXEL XL330-M288-T that drives the child link through an FPX330-H101 hinge frame and is seated in the parent link on an FPX330-S102 (radial mount) or FPX330-S101 (lateral mount) frame. The first column gives the unit cost (ROBOTIS US list price, September 2026) and the remaining columns the quantity used by each design; PLA is counted by mass. Totals are rounded to the nearest dollar. a Sold in sets of four; unit cost is one quarter of the set price. b One cable ships with every actuator, so cables add no cost. c M3 heat-set insert cost is based on a 100-pack of Uxcell M3

\times

6 mm brass heat-set inserts (5 mm OD) at

12.69. PLA cost is estimated at

0.02/g, with mass estimated from the printed volume at the effective printed density.

Robotic Manipulation

Robotic manipulation studies how robots perceive, plan, and control physical interactions to grasp, move, assemble, and use objects.

See all 1,685 papers

Dec 3, 2025

House of Dextra: Cross-embodied Co-design for Dexterous Hands

Dexterous manipulation is limited by both control and design, without consensus as to what makes manipulators best for performing dexterous tasks. This raises a fundamental challenge: how should we design and control robot manipulators that are optimized for dexterity? We present a co-design framework that learns task-specific hand morphology and complementary dexterous control policies. The framework supports 1) an expansive morphology search space including joint, finger, and palm generation, 2) scalable evaluation across the wide design space via morphology-conditioned cross-embodied control, and 3) real-world fabrication with accessible components. We evaluate the approach across multiple dexterous tasks, including in-hand rotation with simulation and real deployment. Our framework enables an end-to-end pipeline that can design, train, fabricate, and deploy a new robotic hand in under 24 hours. The full framework and generated robot hands are open-sourced and available on our website.

Kehlani Fay, Darin Anthony Djapri, Anya Zorin +6

University of California, San Diego · University of California, Santa Barbara

Robotic Hand Design Dexterous Manipulation Robot Morphology-Control Co-Design Cross-Embodiment Robot Learning Robotics

Ask PDF

May 22, 2026

ECo-MoE: Embodiment-Conditioned Mixture of Experts Increases the Evolvability of Robots

In this paper, we introduce a model of evolution and learning in robots that co-optimizes a distribution of latent design vectors (genotypes) and a mixture of control experts (neural modules), which are gated by the latent coordinates of each decoded design (phenotype). This provides a scalable alternative to co-design algorithms that either train an individual policy for every robot, which is inefficient, or a monolithic universal controller for all robots, which results in overly conservative structures and behaviors. Our approach lies somewhere between these two extremes, preserving ancestral knowledge in a unified yet modular framework in which different body plans activate and deactivate different combinations of learned sensorimotor circuits for goal-directed behavior. This allows one part of the controller to be overhauled to better suit new species of designs as they emerge without disrupting the hard-earned knowledge contained within other expert modules. It also allows pretrained expert policies to be directly plugged into the mixture, which can steer evolution into otherwise unexplored areas of latent space containing desired morphological traits. We refer to this process as "evo by demo" and explore how it may be used to guide freeform evolution toward canonical structures defined by the pretrained model. Videos and code can be found at: https://eco-moe.github.io.

Yibin Wang, Muhan Li, Zihan Guo +1

Northwestern University, Evanston, IL, USA.

Robot Morphology-Control Co-Design Mixture of Experts Cross-Embodiment Robot Learning Robotics Evolutionary Robotics

Ask PDF

Aug 24, 2026

Shaping the Evolutionary Dynamics of Robot Morphology via Adaptive Control Learning

Robot co-design via bi-level optimization couples within-lifetime controller learning for fitness evaluation with cross-generational morphological evolution. Prior work has established that well-adapted morphology facilitates faster control learning, a property termed morphological intelligence. Yet how control learning reciprocally shapes morphological evolution remains unexplored. This paper examines both directions for a holistic account of brain-body interplay. We first show that morphological contributions to control learning decouple into two orthogonal dimensions. We formalize the convergence speed as morphological intelligence and identify the performance ceiling as a complementary quantity termed true potential. A concise functional relation is then established to jointly characterize both quantities from individual learning curves, which, when aggregated at the population level, capture evolutionary profiles. Through extensive experiments on simulated voxel-based soft robots, we reveal that premature fitness evaluation systematically underestimates true potential and biases selection towards fast learners. This restricts design space exploration, compromising both optimization efficiency and morphological diversity. Notably, the widely recognized morphological Baldwin effect emerges as an artifact of this bias rather than a general evolutionary tendency. We therefore propose AdaControl, which monitors disproportionate selection for morphological intelligence during evolution and allocates minimally sufficient control learning for unbiased fitness evaluation. With AdaControl, a simple genetic algorithm rivals state-of-the-art generative-model-based co-design methods in discovering diverse high-performing designs while cutting computation by up to 80% versus exhaustive control.

Junru Song, Yang Yang, Yaqing Xu +5

Shanghai Jiao Tong University, Shanghai 200240, China · Intelligent Game and Decision Laboratory, Beijing 100048, China · Renmin University of China, Beijing 100872, China +1

Robot Morphology-Control Co-Design Evolutionary Robotics Embodied Cognition

Ask PDF

Abstract

Robotic Manipulation

Explore similar work

House of Dextra: Cross-embodied Co-design for Dexterous Hands

ECo-MoE: Embodiment-Conditioned Mixture of Experts Increases the Evolvability of Robots

Shaping the Evolutionary Dynamics of Robot Morphology via Adaptive Control Learning