IP Library › Granted Patent US 12,722,286
Granted Patent B2
US 12,722,286 · App. 18/610,285 · Granted Sep 1, 2026

Learning robust legged robot locomotion with implicit terrain imagination via deep reinforcement learning

Inventors: Hyun Myung (Daejeon, KR); I Made Aswin Nahrendra (Daejeon, KR); Byeongho Yu (Daejeon, KR)
Assignee: UROBOTICS CORP.
B25J9/1602B25J13/088B62D57/032
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,722,286
App. No.
18/610,285
Granted
Sep 1, 2026
Kind
B2
Abstract

Disclosed is technology for controlling deep reinforcement learning-based legged robot locomotion by inferring implicit terrain information. A legged robot control method may include inferring an action of a quadrupedal robot from proprioception through a deep reinforcement learning-legged robot model, and a locomotion policy that implicitly infers properties of terrains through which the quadrupedal robot moves may be learned in the legged robot model.

Claims (27)

1 . A legged robot control method performed by a computer device,

wherein the computer device comprises at least one processor configured to execute computer-readable instructions included in a memory,

the legged robot control method comprises inferring, by the at least one processor, an action of a quadrupedal robot from proprioception through a deep reinforcement learning-legged robot model, and

a locomotion policy that implicitly infers properties of terrains through which the quadrupedal robot moves is learned in the legged robot model, wherein (a) a context-aided estimator that estimates surrounding environmental information during a learning process of the locomotion policy is jointly learned in the legged robot model, (b) the legged robot model is a neural network that infers the action when a proprioceptive observation, a body velocity, and a latent state are given as a policy network configured as an actor network in an asymmetric actor-critic network, and (c) the context-aided estimator is optimized using a hybrid loss function that includes body velocity estimation loss and variational auto-encoder (VAE) loss.

2 . The legged robot control method of claim 1 , wherein a locomotion policy that enables a blind locomotion of the quadrupedal robot using an asymmetric actor-critic architecture is learned in the legged robot model.

3 . The legged robot control method of claim 1 , wherein the policy network is trained with an interplay with a value network configured as a critic network in the asymmetric actor-critic network, and the value network is trained using a disturbance force randomly applied to a robot's body and height information of the robot's surrounding environment.

4 . The legged robot control method of claim 1 , wherein the proprioceptive observation is measured using a joint encoder and an inertial measurement unit (IMU), and the body velocity and the latent state are estimated using the context-aided estimator.

5 . The legged robot control method of claim 1 , wherein the proprioceptive observation includes at least one of a body angular velocity, a gravity vector in a body frame, a body velocity command, a joint angle, a joint angular velocity, and a previous action.

6 . The legged robot control method of claim 1 , wherein the policy network is trained to infer a joint angle around a robot's stand still pose.

7 . The legged robot control method of claim 1 , wherein the context-aided estimator includes a body velocity estimation model and an auto-encoder model that shares a unified encoder.

8 . The legged robot control method of claim 1 , wherein the context-aided estimator includes a single encoder and a multi-head decoder and encodes the proprioceptive observation into the body velocity and the latent state through the encoder.

9 . The legged robot control method of claim 1 , wherein a power distribution reward for a motor used on the robot is included in a reward function to train the policy network.

10 . A legged robot control method performed by a computer device, wherein the computer device comprises at least one processor configured to execute computer-readable instructions included in a memory, the legged robot control method comprises inferring, by the at least one processor, an action of a quadrupedal robot from proprioception through a deep reinforcement learning-legged robot model, and a locomotion policy that implicitly infers properties of terrains through which the quadrupedal robot moves is learned in the legged robot model, wherein (a) a context-aided estimator that estimates surrounding environmental information during a learning process of the locomotion policy is jointly learned in the legged robot model, (b) the legged robot model is a neural network that infers the action when a proprioceptive observation, a body velocity, and a latent state are given as a policy network configured as an actor network in an asymmetric actor-critic network, and (c) the context-aided estimator is optimized using a hybrid loss function that includes body velocity estimation loss and variational auto-encoder (VAE) loss, and (d) adaptive bootstrapping for adaptively tuning a bootstrapping probability is performed according to a reward coefficient of variation by the context-aided estimator during training of the policy network.

11 . A non-transitory computer-readable recording medium storing instructions that, when executed by a processor, cause the processor to perform a legged robot control method comprising inferring an action of a quadrupedal robot from proprioception through a deep reinforcement learning-legged robot model, wherein a locomotion policy that implicitly infers properties of terrains through which the quadrupedal robot moves is learned in the legged robot model, wherein (a) a context-aided estimator that estimates surrounding environmental information during a learning process of the locomotion policy is jointly learned in the legged robot model, (b) the legged robot model is a neural network that infers the action when a proprioceptive observation, a body velocity, and a latent state are given as a policy network configured as an actor network in an asymmetric actor-critic network, and (c) the context-aided estimator is optimized using a hybrid loss function that includes body velocity estimation loss and variational auto-encoder (VAE) loss.

12 . A computer-implemented legged robot control system comprising:

at least one processor configured to execute computer-readable instructions included in a memory,

wherein the at least one processor is configured to process a process of inferring an action of a quadrupedal robot from proprioception through a deep reinforcement learning-legged robot model, and

a locomotion policy that implicitly infers properties of terrains through which the quadrupedal robot moves is learned in the legged robot model, wherein (a) a context-aided estimator that estimates surrounding environmental information during a learning process of the locomotion policy is jointly learned in the legged robot model, (b) the legged robot model is a neural network that infers the action when a proprioceptive observation, a body velocity, and a latent state are given as a policy network configured as an actor network in an asymmetric actor-critic network, and (c) the context-aided estimator is optimized using a hybrid loss function that includes body velocity estimation loss and variational auto-encoder (VAE) loss.

13 . The legged robot control system of claim 12 , wherein:

the policy network is trained with an interplay with a value network configured as a critic network in the asymmetric actor-critic network, and

the value network is trained using a disturbance force randomly applied to a robot's body and height information of the robot's surrounding environment.

14 . The legged robot control system of claim 13 , wherein:

the proprioceptive observation is measured using a joint encoder and an inertial measurement unit (IMU),

the body velocity and the latent state are estimated using the context-aided estimator, and

the context-aided estimator includes a single encoder and a multi-head decoder and encodes the proprioceptive observation into the body velocity and the latent state through the encoder.

15 . The legged robot control system of claim 13 , wherein a power distribution reward for a motor used on the robot is included in a reward function to train the policy network.

16 . The legged robot control system of claim 13 , wherein adaptive bootstrapping for adaptively tuning a bootstrapping probability is performed according to a reward coefficient of variation by the context-aided estimator during training of the policy network.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 5, 2026
From: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY
To: UROBOTICS CORP.
Reel/Frame 073977/0594 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 20, 2024
From: MYUNG, HYUN; NAHRENDRA, I MADE ASWIN; YU, BYEONGHO
To: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY
Reel/Frame 066831/0676 →
Priority Claims (1)
KR 10-2023-0089039 · Jul 10, 2023 · national
Continuity (1)
Related Publication 20250018560A1 · Jan 16, 2025
References Cited (10)
US 11868882B2 · Pietquin · 2024 [cited by examiner]
US 12151380B2 · Whitman · 2024 [cited by examiner]
US 20210397961A1 · Choi · 2021 [cited by examiner]
US 20240116170A1 · Luo · 2024 [cited by examiner]
KR 20090126090A · 2009 [cited by examiner]
Fu, Zipeng, et al. “Minimizing energy consumption leads to the emergence of gaits in legged robots.” arXiv preprint arXiv:2111.01674 (2021) (Year: 2021). [cited by examiner]
(G. Ji, J. Mun, H. Kim and J. Hwangbo, “Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotion,” in IEEE Robotics and Automation Letters, vol. 7, No. 2, pp. 4630-4637, Apr… [cited by examiner]
Lee, Joonho, Jemin Hwangbo, and Marco Hutter. “Robust recovery controller for a quadrupedal robot using deep reinforcement learning.” arXiv preprint arXiv:1901.07517 (Year: 2019). [cited by examiner]
L. Ren, C. Wang, Y. Yang and Z. Cao, “A learning-based control approach for blind quadrupedal locomotion with guided-DRL and hierarchical-DRL,” 2021 IEEE International Conference on Robotics and Biomimetics (ROBIO), San… [cited by examiner]
Translation of KR-20090126090-A (Year: 2009). [cited by examiner]