Zhanpeng He

Siddharth Singi, Zhanpeng He, Alvin Pan et al.

In a Human-in-the-Loop paradigm, a robotic agent is able to act mostly autonomously in solving a task, but can request help from an external expert when needed. However, knowing when to request such assistance is critical: too few requests can lead to the robot making mistakes, but too many requests can overload the expert. In this paper, we present a Reinforcement Learning based approach to this problem, where a semi-autonomous agent asks for external assistance when it has low confidence in the eventual success of the task. The confidence level is computed by estimating the variance of the return from the current state. We show that this estimate can be iteratively improved during training using a Bellman-like recursion. On discrete navigation problems with both fully- and partially-observable state information, we show that our method makes effective use of a limited budget of expert calls at run-time, despite having no access to the expert at training time.

Zhanpeng He, Matei Ciocarlie

We introduce MORPH, a method for co-optimization of hardware design parameters and control policies in simulation using reinforcement learning. Like most co-optimization methods, MORPH relies on a model of the hardware being optimized, usually simulated based on the laws of physics. However, such a model is often difficult to integrate into an effective optimization routine. To address this, we introduce a proxy hardware model, which is always differentiable and enables efficient co-optimization alongside a long-horizon control policy using RL. MORPH is designed to ensure that the optimized hardware proxy remains as close as possible to its realistic counterpart, while still enabling task completion. We demonstrate our approach on simulated 2D reaching and 3D multi-fingered manipulation tasks.

Sharfin Islam, Zewen Chen, Zhanpeng He et al.

Bimanual robot manipulators can achieve impressive dexterity, but typically rely on two full six- or seven- degree-of-freedom arms so that paired grippers can coordinate effectively. This traditional framework increases system complexity while only exploiting a fraction of the overall workspace for dexterous interaction. We introduce the MiniBEE (Miniature Bimanual End-effector), a compact system in which two reduced-mobility arms (3+ DOF each) are coupled into a kinematic chain that preserves full relative positioning between grippers. To guide our design, we formulate a kinematic dexterity metric that enlarges the dexterous workspace while keeping the mechanism lightweight and wearable. The resulting system supports two complementary modes: (i) wearable kinesthetic data collection with self-tracked gripper poses, and (ii) deployment on a standard robot arm, extending dexterity across its entire workspace. We present kinematic analysis and design optimization methods for maximizing dexterous range, and demonstrate an end-to-end pipeline in which wearable demonstrations train imitation learning policies that perform robust, real-world bimanual manipulation.

Tianhe Yu, Deirdre Quillen, Zhanpeng He et al.

Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task distributions that are very narrow. For example, a commonly used meta-reinforcement learning benchmark uses different running velocities for a simulated robot as different tasks. When policies are meta-trained on such narrow task distributions, they cannot possibly generalize to more quickly acquire entirely new tasks. Therefore, if the aim of these methods is to enable faster acquisition of entirely new behaviors, we must evaluate them on task distributions that are sufficiently broad to enable generalization to new behaviors. In this paper, we propose an open-source simulated benchmark for meta-reinforcement learning and multi-task learning consisting of 50 distinct robotic manipulation tasks. Our aim is to make it possible to develop algorithms that generalize to accelerate the acquisition of entirely new, held-out tasks. We evaluate 7 state-of-the-art meta-reinforcement learning and multi-task learning algorithms on these tasks. Surprisingly, while each task and its variations (e.g., with different object positions) can be learned with reasonable success, these algorithms struggle to learn with multiple tasks at the same time, even with as few as ten distinct training tasks. Our analysis and open-source environments pave the way for future research in multi-task learning and meta-learning that can enable meaningful generalization, thereby unlocking the full potential of these methods.

Zhanpeng He, Yifeng Cao, Matei Ciocarlie

Human-in-the-loop (HitL) robot deployment has gained significant attention in both academia and industry as a semi-autonomous paradigm that enables human operators to intervene and adjust robot behaviors at deployment time, improving success rates. However, continuous human monitoring and intervention can be highly labor-intensive and impractical when deploying a large number of robots. To address this limitation, we propose a method that allows diffusion policies to actively seek human assistance only when necessary, reducing reliance on constant human oversight. To achieve this, we leverage the generative process of diffusion policies to compute an uncertainty-based metric based on which the autonomous agent can decide to request operator assistance at deployment time, without requiring any operator interaction during training. Additionally, we show that the same method can be used for efficient data collection for fine-tuning diffusion policies in order to improve their autonomous performance. Experimental results from simulated and real-world environments demonstrate that our approach enhances policy performance during deployment for a variety of scenarios.

Zhanpeng He, Matei Ciocarlie

Controlling robotic manipulators with high-dimensional action spaces for dexterous tasks is a challenging problem. Inspired by human manipulation, researchers have studied generating and using postural synergies for robot hands to accomplish manipulation tasks, leveraging the lower dimensional nature of synergistic action spaces. However, many of these works require pre-collected data from an existing controller in order to derive such a subspace by means of dimensionality reduction. In this paper, we present a framework that simultaneously discovers a synergy space and a multi-task policy that operates on this low-dimensional action space to accomplish diverse manipulation tasks. We demonstrate that our end-to-end method is able to perform multiple tasks using few synergies, and outperforms sequential methods that apply dimensionality reduction to independently collected data. We also show that deriving synergies using multiple tasks can lead to a subspace that enables robots to efficiently learn new manipulation tasks and interactions with new objects.

Zhenjia Xu, Zhanpeng He, Shuran Song

We introduce the Universal Manipulation Policy Network (UMPNet) -- a single image-based policy network that infers closed-loop action sequences for manipulating arbitrary articulated objects. To infer a wide range of action trajectories, the policy supports 6DoF action representation and varying trajectory length. To handle a diverse set of objects, the policy learns from objects with different articulation structures and generalizes to unseen objects or categories. The policy is trained with self-guided exploration without any human demonstrations, scripted policy, or pre-defined goal conditions. To support effective multi-step interaction, we introduce a novel Arrow-of-Time action attribute that indicates whether an action will change the object state back to the past or forward into the future. With the Arrow-of-Time inference at each interaction step, the learned policy is able to select actions that consistently lead towards or away from a given state, thereby, enabling both effective state exploration and goal-conditioned manipulation. Video is available at https://youtu.be/KqlvcL9RqKM

Zhenjia Xu, Zhanpeng He, Jiajun Wu et al.

3D scene representation for robot manipulation should capture three key object properties: permanency -- objects that become occluded over time continue to exist; amodal completeness -- objects have 3D occupancy, even if only partial observations are available; spatiotemporal continuity -- the movement of each object is continuous over space and time. In this paper, we introduce 3D Dynamic Scene Representation (DSR), a 3D volumetric scene representation that simultaneously discovers, tracks, reconstructs objects, and predicts their dynamics while capturing all three properties. We further propose DSR-Net, which learns to aggregate visual observations over multiple interactions to gradually build and refine DSR. Our model achieves state-of-the-art performance in modeling 3D scene dynamics with DSR on both simulated and real data. Combined with model predictive control, DSR-Net enables accurate planning in downstream robotic manipulation tasks such as planar pushing. Video is available at https://youtu.be/GQjYG3nQJ80.

Tianjian Chen, Zhanpeng He, Matei Ciocarlie

Deep Reinforcement Learning (RL) has shown great success in learning complex control policies for a variety of applications in robotics. However, in most such cases, the hardware of the robot has been considered immutable, modeled as part of the environment. In this study, we explore the problem of learning hardware and control parameters together in a unified RL framework. To achieve this, we propose to model the robot body as a "hardware policy", analogous to and optimized jointly with its computational counterpart. We show that, by modeling such hardware policies as auto-differentiable computational graphs, the ensuing optimization problem can be solved efficiently by gradient-based algorithms from the Policy Optimization family. We present two such design examples: a toy mass-spring problem, and a real-world problem of designing an underactuated hand. We compare our method against traditional co-optimization approaches, and also demonstrate its effectiveness by building a physical prototype based on the learned hardware parameters. Videos and more details are available at https://roamlab.github.io/hwasp/ .

Bohan Wu, Feng Xu, Zhanpeng He et al.

Recent advances in deep reinforcement learning (RL) have demonstrated its potential to learn complex robotic manipulation tasks. However, RL still requires the robot to collect a large amount of real-world experience. To address this problem, recent works have proposed learning from expert demonstrations (LfD), particularly via inverse reinforcement learning (IRL), given its ability to achieve robust performance with only a small number of expert demonstrations. Nevertheless, deploying IRL on real robots is still challenging due to the large number of robot experiences it requires. This paper aims to address this scalability challenge with a robust, sample-efficient, and general meta-IRL algorithm, SQUIRL, that performs a new but related long-horizon task robustly given only a single video demonstration. First, this algorithm bootstraps the learning of a task encoder and a task-conditioned policy using behavioral cloning (BC). It then collects real-robot experiences and bypasses reward learning by directly recovering a Q-function from the combined robot and expert trajectories. Next, this algorithm uses the Q-function to re-evaluate all cumulative experiences collected by the robot to improve the policy quickly. In the end, the policy performs more robustly (90%+ success) than BC on new tasks while requiring no trial-and-errors at test time. Finally, our real-robot and simulated experiments demonstrate our algorithm's generality across different state spaces, action spaces, and vision-based manipulation tasks, e.g., pick-pour-place and pick-carry-drop.

Zhanpeng He, Ryan Julian, Eric Heiden et al.

Simulation-to-real transfer is an important strategy for making reinforcement learning practical with real robots. Successful sim-to-real transfer systems have difficulty producing policies which generalize across tasks, despite training for thousands of hours equivalent real robot time. To address this shortcoming, we present a novel approach to efficiently learning new robotic skills directly on a real robot, based on model-predictive control (MPC) and an algorithm for learning task representations. In short, we show how to reuse the simulation from the pre-training step of sim-to-real methods as a tool for foresight, allowing the sim-to-real policy adapt to unseen tasks. Rather than end-to-end learning policies for single tasks and attempting to transfer them, we first use simulation to simultaneously learn (1) a continuous parameterization (i.e. a skill embedding or latent) of task-appropriate primitive skills, and (2) a single policy for these skills which is conditioned on this representation. We then directly transfer our multi-skill policy to a real robot, and actuate the robot by choosing sequences of skill latents which actuate the policy, with each latent corresponding to a pre-learned primitive skill controller. We complete unseen tasks by choosing new sequences of skill latents to control the robot using MPC, where our MPC model is composed of the pre-trained skill policy executed in the simulation environment, run in parallel with the real robot. We discuss the background and principles of our method, detail its practical implementation, and evaluate its performance by using our method to train a real Sawyer Robot to achieve motion tasks such as drawing and block pushing.

Ryan Julian, Eric Heiden, Zhanpeng He et al.

We present a novel solution to the problem of simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than focusing on minimizing the simulation-reality gap, we learn a set of diverse policies that are parameterized in a way that makes them easily reusable. This diversity and parameterization of low-level skills allows us to find a transferable policy that is able to use combinations and variations of different skills to solve more complex, high-level tasks. In particular, we first use simulation to jointly learn a policy for a set of low-level skills, and a "skill embedding" parameterization which can be used to compose them. Later, we learn high-level policies which actuate the low-level policies via this skill embedding parameterization. The high-level policies encode how and when to reuse the low-level skills together to achieve specific high-level tasks. Importantly, our method learns to control a real robot in joint-space to achieve these high-level tasks with little or no on-robot time, despite the fact that the low-level policies may not be perfectly transferable from simulation to real, and that the low-level skills were not trained on any examples of high-level tasks. We illustrate the principles of our method using informative simulation experiments. We then verify its usefulness for real robotics problems by learning, transferring, and composing free-space and contact motion skills on a Sawyer robot using only joint-space control. We experiment with several techniques for composing pre-learned skills, and find that our method allows us to use both learning-based approaches and efficient search-based planning to achieve high-level tasks using only pre-learned skills.