Auxiliary Tasks and Exploration Enable ObjectNav

8 Apr 2021  ·  Joel Ye, Dhruv Batra, Abhishek Das, Erik Wijmans ·

ObjectGoal Navigation (ObjectNav) is an embodied task wherein agents are to navigate to an object instance in an unseen environment. Prior works have shown that end-to-end ObjectNav agents that use vanilla visual and recurrent modules, e.g. a CNN+RNN, perform poorly due to overfitting and sample inefficiency. This has motivated current state-of-the-art methods to mix analytic and learned components and operate on explicit spatial maps of the environment. We instead re-enable a generic learned agent by adding auxiliary learning tasks and an exploration reward. Our agents achieve 24.5% success and 8.1% SPL, a 37% and 8% relative improvement over prior state-of-the-art, respectively, on the Habitat ObjectNav Challenge. From our analysis, we propose that agents will act to simplify their visual inputs so as to smooth their RNN dynamics, and that auxiliary tasks reduce overfitting by minimizing effective RNN dimensionality; i.e. a performant ObjectNav agent that must maintain coherent plans over long horizons does so by learning smooth, low-dimensional recurrent dynamics. Site:

PDF Abstract


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Robot Navigation Habitat 2020 Object Nav test-std 6-Act Tether SPL 0.08378 # 2
SOFT_SPL 0.1655 # 4
DISTANCE_TO_GOAL 9.14796 # 10
SUCCESS 0.21082 # 1


No methods listed for this paper. Add relevant methods here