The Panda3D Graphics Engine

By Mike Goslin, M. Mine. 2004

114 citations recorded by the source corpus.

Subfields: Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

Citations in the corpus

Self-Supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation (2017, methodology): “Bullet physics simulator and images were rendered using the Panda3d graphics engine [31].”
Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation (2018, methodology): “The simulator is built on the Bullet physics engine [37] and uses Panda3d [38] for image rendering.”
To Fall Or Not To Fall: A Visual Approach to Physical Stability Prediction (2016, positive): “Physics Engine We use Bullet [8] physics engine in Panda3D [11] to perform physics-based simulation for 2000ms at 1000Hz for each scene.”
Visual Stability Prediction and Its Application to Manipulation (2016, methodology): “Images are rendered at resolution of 800× 800 in color. f) Physics Engine: We use Bullet [25] in Panda3D [26] to perform physics-based simulation for 2s at 1000Hz for each scene.”
MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning (2021, methodology): “In low-level implementation, we encapsulate the back-end implementation of the basic components and the intercommunication between Python API and the extremely efﬁcient 3D game engine Panda3D [12]. convenient and ﬂexible for RL researchers to develop new scenarios and tasks to prototype their method”
HoME: a Household Multimodal Environment (2017, methodology): “ up, drop, push). HoME also enables multiple agents to be spawned at once. The following sections detail HoME’s core components. 3.1 Rendering engine The rendering engine is implemented using Panda3D [39], an open-source 3D game engine which ships with complete Python bindings. For each SUNCG house,”
Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following (2020, unknown): “[48] M.”