{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fleet-dagger-interactive-robot-fleet-learning","title":"Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision","arxiv_id":"2206.14349","date":"2022-06-29","proceeding":null,"authors":["Ryan Hoque","Lawrence Yunliang Chen","Satvik Sharma","Karthik Dharmarajan","Brijen Thananjeyan","Pieter Abbeel","Ken Goldberg"],"abstract":"Commercial and industrial deployments of robot fleets at Amazon, Nimble, Plus One, Waymo, and Zoox query remote human teleoperators when robots are at risk or unable to make task progress. With continual learning, interventions from the remote pool of humans can also be used to improve the robot fleet control policy over time. A central question is how to effectively allocate limited human attention. Prior work addresses this in the single-robot, single-human setting; we formalize the Interactive Fleet Learning (IFL) setting, in which multiple robots interactively query and learn from multiple human supervisors. We propose Return on Human Effort (ROHE) as a new metric and Fleet-DAgger, a family of IFL algorithms. We present an open-source IFL benchmark suite of GPU-accelerated Isaac Gym environments for standardized evaluation and development of IFL algorithms. We compare a novel Fleet-DAgger algorithm to 4 baselines with 100 robots in simulation. We also perform a physical block-pushing experiment with 4 ABB YuMi robot arms and 2 remote humans. Experiments suggest that the allocation of humans to robots significantly affects the performance of the fleet, and that the novel Fleet-DAgger algorithm can achieve up to 8.8x higher ROHE than baselines. See https://tinyurl.com/fleet-dagger for supplemental material.","url_abs":"https://arxiv.org/abs/2206.14349v2","url_pdf":"https://arxiv.org/pdf/2206.14349v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fleet-dagger-interactive-robot-fleet-learning","repo_url":"https://github.com/berkeleyautomation/ifl_benchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.14349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.14349"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/berkeleyautomation/ifl_benchmark","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"unverified":8},"by_repo_kind":{"official":{"samples":9,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"8c881242a42896d3","entry":"torchify","repo":"berkeleyautomation/ifl_benchmark","repo_kind":"official","path":"iflb/parallel_experiment.py","file_url":"https://github.com/berkeleyautomation/ifl_benchmark/blob/HEAD/iflb/parallel_experiment.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8c881242a42896d3"}},{"code_sha256_prefix":"608bee081752d87e","entry":"compute_ant_reward","repo":"berkeleyautomation/ifl_benchmark","repo_kind":"official","path":"env/isaacgym/ant.py","file_url":"https://github.com/berkeleyautomation/ifl_benchmark/blob/HEAD/env/isaacgym/ant.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"608bee081752d87e"}},{"code_sha256_prefix":"47a2ff40aedf9f82","entry":"compute_bbot_reward","repo":"berkeleyautomation/ifl_benchmark","repo_kind":"official","path":"env/isaacgym/ball_balance.py","file_url":"https://github.com/berkeleyautomation/ifl_benchmark/blob/HEAD/env/isaacgym/ball_balance.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"47a2ff40aedf9f82"}},{"code_sha256_prefix":"e7f63143a253f9c6","entry":"compute_stats","repo":"berkeleyautomation/ifl_benchmark","repo_kind":"official","path":"plotting/process_logs.py","file_url":"https://github.com/berkeleyautomation/ifl_benchmark/blob/HEAD/plotting/process_logs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7f63143a253f9c6"}},{"code_sha256_prefix":"88ae3a84a23a1bf9","entry":"get_offline_data","repo":"berkeleyautomation/ifl_benchmark","repo_kind":"official","path":"env/navigation.py","file_url":"https://github.com/berkeleyautomation/ifl_benchmark/blob/HEAD/env/navigation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88ae3a84a23a1bf9"}},{"code_sha256_prefix":"18c7c52ef841c0d4","entry":"make_env","repo":"berkeleyautomation/ifl_benchmark","repo_kind":"official","path":"env/make_utils.py","file_url":"https://github.com/berkeleyautomation/ifl_benchmark/blob/HEAD/env/make_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"18c7c52ef841c0d4"}},{"code_sha256_prefix":"056564dc1eae1a84","entry":"process_action","repo":"berkeleyautomation/ifl_benchmark","repo_kind":"official","path":"env/navigation.py","file_url":"https://github.com/berkeleyautomation/ifl_benchmark/blob/HEAD/env/navigation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"056564dc1eae1a84"}},{"code_sha256_prefix":"2fc680e2a66e941c","entry":"teacher_action","repo":"berkeleyautomation/ifl_benchmark","repo_kind":"official","path":"env/navigation.py","file_url":"https://github.com/berkeleyautomation/ifl_benchmark/blob/HEAD/env/navigation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2fc680e2a66e941c"}},{"code_sha256_prefix":"d111e1d4d2700dcf","entry":"wrap_to_pi","repo":"berkeleyautomation/ifl_benchmark","repo_kind":"official","path":"env/isaacgym/anymal_terrain.py","file_url":"https://github.com/berkeleyautomation/ifl_benchmark/blob/HEAD/env/isaacgym/anymal_terrain.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d111e1d4d2700dcf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}