Data collection in robotics is spread across diverse hardware, and this variation will increase as new hardware is developed. Effective use of this growing body of data requires methods capable of learning from diverse robot embodiments. We consider the setting of training a policy using expert trajectories from a single robot arm (the source), and evaluating on a different robot arm for which no data was collected (the target). We present a data editing scheme termed Shadow, in which the robot during training and evaluation is replaced with a composite segmentation mask of the source and target robots. In this way, the input data distribution at train and test time match closely, enabling robust policy transfer to the new unseen robot while being far more data efficient than approaches that require co-training on large amounts of data from diverse embodiments. We demonstrate that an approach as simple as Shadow is effective both in simulation on varying tasks and robots, and on real robot hardware, where Shadow demonstrates an average of over 2x improvement in success rate compared to the strongest baseline.

The ability to reuse collected data and transfer trained policies between robots could alleviate the burden of additional data collection and training. While existing approaches such as pretraining plus finetuning and co-training show promise, they do not generalize to robots unseen in training. Focusing on common robot arms with similar workspaces and 2-jaw grippers, we investigate the feasibility of zero-shot transfer. Through simulation studies on 8 manipulation tasks, we find that state-based Cartesian control policies can successfully zero-shot transfer to a target robot after accounting for forward dynamics. To address robot visual disparities for vision-based policies, we introduce Mirage, which uses "cross-painting"--masking out the unseen target robot and inpainting the seen source robot--during execution in real time so that it appears to the policy as if the trained source robot were performing the task. Mirage applies to both first-person and third-person camera views and policies that take in both states and images as inputs or only images as inputs. Despite its simplicity, our extensive simulation and physical experiments provide strong evidence that Mirage can successfully zero-shot transfer between different robot arms and grippers with only minimal performance degradation on a variety of manipulation tasks such as picking, stacking, and assembly, significantly outperforming a generalist policy. Project website: https://robot-mirage.github.io/

Therefore, to transfer a policy on the source robot to multiple target robots, they must launch multiple independent runs for each target robot. We investigate the problem of transferring an expert policy from a source robot to multiple different robots. To solve this problem, we propose a method named Meta-Evolve that uses continuous robot evolution to efficiently transfer the policy to each target robot through a set of tree-structured evolutionary robot sequences. The robot evolution tree allows the robot evolution paths to be shared, so our approach can significantly outperform naive one-to-one policy transfer. We present a heuristic approach to determine an optimized robot evolution tree. Experiments have shown that our method is able to improve the efficiency of one-to-three transfer of manipulation policy by up to 3.2 and one-to-six transfer of agile locomotion policy by 2.4 in terms of simulation cost over the baseline of launching multiple independent one-to-one policy transfers. The robotics industry has designed and developed a large number of commercial robots deployed in various applications. How to efficiently learn robotic skills on diverse robots in a scalable fashion? A popular solution is to train a policy for every new robot on every new task from scratch. This is not only inefficient in terms of sample efficiency but also impractical for complex robots due to a large exploration space. Inter-robot imitation by statistic matching methods that optimize to match the distribution of actions (Ross et al., 2011), transitioned states (Liu et al., 2019; Radosavovic et al., 2020), or reward (Ng et al., 2000; Ho & Ermon, 2016) could be possible solutions. However, they can only be applied to robots with similar dynamics to yield optimal performance. Recent advances in evolution-based imitation learning (Liu et al., 2022a;b) inspire us to view this problem from the perspective of policy transferring from one robot to another. The core idea is to interpolate two different robots by producing a large number of intermediate robots between them which gradually evolve from the source robot toward the target robot.

Humans learn about objects via interaction and using multiple perceptions, such as vision, sound, and touch. While vision can provide information about an object's appearance, non-visual sensors, such as audio and haptics, can provide information about its intrinsic properties, such as weight, temperature, hardness, and the object's sound. Using tools to interact with objects can reveal additional object properties that are otherwise hidden (e.g., knives and spoons can be used to examine the properties of food, including its texture and consistency). Robots can use tools to interact with objects and gather information about their implicit properties via non-visual sensors. However, a robot's model for recognizing objects using a tool-mediated behavior does not generalize to a new tool or behavior due to differing observed data distributions. To address this challenge, we propose a framework to enable robots to transfer implicit knowledge about granular objects across different tools and behaviors. The proposed approach learns a shared latent space from multiple robots' contexts produced by respective sensory data while interacting with objects using tools. We collected a dataset using a UR5 robot that performed 5,400 interactions using 6 tools and 6 behaviors on 15 granular objects and tested our method on cross-tool and cross-behavioral transfer tasks. Our results show the less experienced target robot can benefit from the experience gained from the source robot and perform recognition on a set of novel objects. We have released the code, datasets, and additional results: https://github.com/gtatiya/Tool-Knowledge-Transfer.

Humans leverage multiple sensor modalities when interacting with objects and discovering their intrinsic properties. Using the visual modality alone is insufficient for deriving intuition behind object properties (e.g., which of two boxes is heavier), making it essential to consider non-visual modalities as well, such as the tactile and auditory. Whereas robots may leverage various modalities to obtain object property understanding via learned exploratory interactions with objects (e.g., grasping, lifting, and shaking behaviors), challenges remain: the implicit knowledge acquired by one robot via object exploration cannot be directly leveraged by another robot with different morphology, because the sensor models, observed data distributions, and interaction capabilities are different across these different robot configurations. To avoid the costly process of learning interactive object perception tasks from scratch, we propose a multi-stage projection framework for each new robot for transferring implicit knowledge of object properties across heterogeneous robot morphologies. We evaluate our approach on the object-property recognition and object-identity recognition tasks, using a dataset containing two heterogeneous robots that perform 7,600 object interactions. Results indicate that knowledge can be transferred across robots, such that a newly-deployed robot can bootstrap its recognition models without exhaustively exploring all objects. We also propose a data augmentation technique and show that this technique improves the generalization of models. We release our code and datasets, here: https://github.com/gtatiya/Implicit-Knowledge-Transfer.

A popular paradigm in robotic learning is to train a policy from scratch for every new robot. This is not only inefficient but also often impractical for complex robots. In this work, we consider the problem of transferring a policy across two different robots with significantly different parameters such as kinematics and morphology. Existing approaches that train a new policy by matching the action or state transition distribution, including imitation learning methods, fail due to optimal action and/or state distribution being mismatched in different robots. In this paper, we propose a novel method named $REvolveR$ of using continuous evolutionary models for robotic policy transfer implemented in a physics simulator. We interpolate between the source robot and the target robot by finding a continuous evolutionary change of robot parameters. An expert policy on the source robot is transferred through training on a sequence of intermediate robots that gradually evolve into the target robot. Experiments show that the proposed continuous evolutionary model can effectively transfer the policy across robots and achieve superior sample efficiency on new robots using a physics simulator. The proposed method is especially advantageous in sparse reward settings where exploration can be significantly reduced.