paper-with-me

Papers

Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation

2022-09-12 · Mohit Shridhar, Lucas Manuelli, Dieter Fox

Transformers have revolutionized vision and natural language processing with their ability to scale with large datasets. But in robotic manipulation, data is both limited and expensive. Can manipulation still benefit from Transformers with the right problem formulation? We investigate this question with PerAct, a language-conditioned behavior-cloning agent for multi-task 6-DoF manipulation. PerAct encodes language goals and RGB-D voxel observations with a Perceiver Transformer, and outputs discretized actions by ``detecting the next best voxel action''. Unlike frameworks that operate on 2D images, the voxelized 3D observation and action space provides a strong structural prior for efficiently learning 6-DoF actions. With this formulation, we train a single multi-task Transformer for 18 RLBench tasks (with 249 variations) and 7 real-world tasks (with 18 variations) from just a few demonstrations per task. Our results show that PerAct significantly outperforms unstructured image-to-action agents and 3D ConvNet baselines for a wide range of tabletop tasks.

📄 PDF Abstract BibTeX arXiv:2209.05451

Code (1)

peract/peract 공식 구현 pytorch

Tasks

Robot ManipulationRobot Manipulation Generalization

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Offline Actor-Critic Reinforcement Learning Scales to Large Models

2024-02-08 · Jost Tobias Springenberg, Abbas Abdolmaleki, Jingwei Zhang, Oliver Groth 외

We show that offline actor-critic reinforcement learning can scale to large models - such as transformers - and follows similar scaling laws as supervised learning. We find that offline actor-critic algorithms can outper…

continuous-controlContinuous ControlOffline RLreinforcement-learning+1

GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields

2023-08-31 · Yanjie Ze, Ge Yan, Yueh-Hua Wu, Annabella Macaluso 외

It is a long-standing problem in robotics to develop agents capable of executing diverse manipulation tasks from visual observations in unstructured real-world environments. To achieve this goal, the robot needs to have …

Decision Making

Multitrack Music Transcription with a Time-Frequency Perceiver

2023-06-19 · Wei-Tsung Lu, Ju-Chiang Wang, Yun-Ning Hung

Multitrack music transcription aims to transcribe a music audio input into the musical notes of multiple instruments simultaneously. It is a very challenging task that typically requires a more complex model to achieve s…

Multi-Task LearningMusic Transcription

AdaPerceiver: Transformers with Adaptive Width, Depth, and Tokens

2025-11-22 · Purvish Jajal, Nick John Eliopoulos, Benjamin Shiue-Hal Chou, George K. Thiruvathukal 외 arxiv

Modern transformer architectures achieve remarkable performance across tasks and domains but remain rigid in how they allocate computation at inference time. Real-world deployment often requires models to adapt to divers…

Semantic SegmentationImage ClassificationDepth Estimation

MilaNLP at SemEval-2022 Task 5: Using Perceiver IO for Detecting Misogynous Memes with Text and Image Modalities

2022-07-01 · SemEval (NAACL) 2022 7 · Giuseppe Attanasio, Debora Nozza, Federico Bianchi

In this paper, we describe the system proposed by the MilaNLP team for the Multimedia Automatic Misogyny Identification (MAMI) challenge. We use Perceiver IO as a multimodal late fusion over unimodal streams to address b…

Image Captioning